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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific function or callback references in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.92
     ſtate
    -0.91
     purpoſe
    -0.89
     itſelf
    -0.88
    ſelf
    -0.84
     Reſ
    -0.82
     ſeveral
    -0.82
     fevere
    -0.81
     STEVEN
    -0.80
     ftate
    -0.79
    POSITIVE LOGITS
    cb
    2.70
    CB
    2.46
     CB
    2.39
     cb
    2.31
    Cb
    1.74
     Cb
    1.58
    cbs
    1.17
    CBM
    1.02
     cbs
    1.00
    cbf
    1.00
    Act Density 0.084%

    No Known Activations