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

    Neuronpedia

    INDEX
    Explanations

    references to data sources and statistics in documents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    !!
    -0.54
    !!!
    -0.53
     ‘
    -0.52
     I
    -0.51
    !
    -0.50
    full
    -0.48
    курс
    -0.48
     Amongst
    -0.48
    oglio
    -0.46
     “
    -0.46
    POSITIVE LOGITS
     itſelf
    0.89
     Majefty
    0.86
     himſelf
    0.84
     poffible
    0.83
     themſelves
    0.79
     Anſ
    0.78
     myſelf
    0.77
     becauſe
    0.77
     doubtnut
    0.76
     Jefus
    0.75
    Act Density 0.113%

    No Known Activations