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

    Neuronpedia

    INDEX
    Explanations

    specific actions or transformations mentioned in a programming or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.74
     …
    -0.63
    .
    -0.60
    LayoutStyle
    -0.57
     می‌کنند
    -0.55
    …
    -0.55
    ?
    -0.54
    ⇔
    -0.53
     нашли
    -0.53
     ...
    -0.52
    POSITIVE LOGITS
     itſelf
    1.23
     raiſ
    1.09
     myſelf
    1.08
     poffe
    1.03
     uſed
    1.01
     Efq
    1.01
     ſind
    0.97
     poffible
    0.96
     photolibrary
    0.95
     Theſe
    0.94
    Act Density 0.340%

    No Known Activations