© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1466
    Prev
    Next
    INDEX
    Explanations

    expressions of personal uncertainty or confusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    覚醒
    -0.86
    geries
    -0.75
    龍契士
    -0.70
    assic
    -0.67
    wered
    -0.67
     裏�
    -0.64
    ��
    -0.64
    imon
    -0.63
    ogyn
    -0.63
     Occupations
    -0.62
    POSITIVE LOGITS
     dunno
    0.91
     mean
    0.88
     agree
    0.83
     personally
    0.78
     hear
    0.76
     know
    0.76
     heard
    0.76
     bet
    0.75
    rons
    0.74
     GOODMAN
    0.74
    Activations Density 0.197%

    No Known Activations