© 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. 690
    Prev
    Next
    INDEX
    Explanations

    expressions of deep emotion or strong feelings

    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
    leys
    -0.95
    エル
    -0.85
    ragon
    -0.79
    ��
    -0.79
    ulton
    -0.78
    gery
    -0.77
    alsh
    -0.74
    nesday
    -0.74
    illions
    -0.74
    nels
    -0.73
    POSITIVE LOGITS
     affected
    0.72
     disappointing
    0.72
     impression
    0.71
     consequential
    0.70
     impacted
    0.70
     disturbed
    0.69
     dependent
    0.68
     concerning
    0.68
     supportive
    0.67
     unsatisf
    0.66
    Activations Density 0.033%

    No Known Activations