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

    Neuronpedia

    INDEX
    Explanations

    the presence of forms of the verb "do"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.70
     the
    -0.65
    —
    -0.60
     a
    -0.59
    ,
    -0.57
    ↵↵
    -0.57
    …
    -0.57
    is
    -0.56
    li
    -0.55
    vi
    -0.54
    POSITIVE LOGITS
    expandindo
    1.30
     مشين
    1.21
    ScopeManager
    1.19
    ագրություններ
    1.15
    BufferException
    1.13
     ModelExpression
    1.12
     виправивши
    1.12
     typelib
    1.12
     Chwiliwch
    1.06
     BoxFit
    1.05
    Act Density 0.275%

    No Known Activations