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

    Neuronpedia

    INDEX
    Explanations

    references to statements or claims made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    一気に
    -0.51
    expandindo
    -0.51
    encodeWith
    -0.49
     kuin
    -0.47
     tartalomajánló
    -0.47
    istream
    -0.47
    )|^{
    -0.45
     TextAppearance
    -0.44
    ModelAdmin
    -0.42
    ríamos
    -0.42
    POSITIVE LOGITS
     earlier
    1.02
     Theſe
    0.85
     somewhere
    0.84
     elsewhere
    0.82
    earlier
    0.80
     itſelf
    0.78
     himſelf
    0.78
     purpoſe
    0.76
     fometimes
    0.75
     Earlier
    0.73
    Act Density 0.289%

    No Known Activations