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

    Neuronpedia

    INDEX
    Explanations

    tab spaces or whitespace characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.67
    and
    -0.66
    <eos>
    -0.60
    …
    -0.57
    So
    -0.57
    of
    -0.54
    so
    -0.54
    <em>
    -0.52
    ah
    -0.51
    go
    -0.50
    POSITIVE LOGITS
    Tikang
    0.98
     myſelf
    0.87
    VersionUID
    0.84
     purpoſe
    0.81
    ArgsConstructor
    0.79
    sizeCache
    0.77
     reaſon
    0.74
     pleaſure
    0.74
     الحره
    0.74
     ainfi
    0.73
    Act Density 0.337%

    No Known Activations