Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    proper names and events

    oai_token-act-pair · gpt-3.5-turbo

    significant actions or events associated with authority figures or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.72
    WF
    -0.70
    %.
    -0.69
     ILCS
    -0.67
    nown
    -0.65
    %);
    -0.64
    scrib
    -0.64
    MON
    -0.63
    INC
    -0.61
    avy
    -0.61
    POSITIVE LOGITS
     hes
    0.63
    perty
    0.60
     KS
    0.57
     JS
    0.56
     Legions
    0.56
     todd
    0.56
     last
    0.56
    uddenly
    0.55
    iculty
    0.55
     Nin
    0.54
    Act Density 0.316%

    No Known Activations