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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 841
    Prev
    Next
    INDEX
    Explanations

    requests or commands for information

    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
    iens
    -0.82
    ��
    -0.78
    geist
    -0.76
     Influence
    -0.71
    matter
    -0.71
    ベ
    -0.71
     horizont
    -0.70
     confir
    -0.66
    condition
    -0.66
    meier
    -0.65
    POSITIVE LOGITS
    uba
    0.72
     VT
    0.70
    roud
    0.70
    SG
    0.67
     Bahá
    0.67
     Scotia
    0.66
     Pension
    0.66
    YY
    0.66
     ya
    0.65
    yy
    0.65
    Activations Density 0.029%

    No Known Activations