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

    Neuronpedia

    INDEX
    Explanations

    adverbs that modify actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _=
    -0.36
     bezpečnost
    -0.35
     OMITBAD
    -0.34
     zajíma
    -0.33
     zimní
    -0.33
     scandalous
    -0.32
    ValueStyle
    -0.32
     pří
    -0.31
    stateMutability
    -0.31
    (()=>
    -0.31
    POSITIVE LOGITS
     had
    0.81
     have
    0.73
     didn
    0.65
     got
    0.65
     gave
    0.62
     drew
    0.61
     did
    0.60
     Оно
    0.58
     looked
    0.58
    LabelTagHelper
    0.58
    Act Density 0.309%

    No Known Activations