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

    Neuronpedia

    INDEX
    Explanations

    verbs and words related to assertions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WriteLiteral
    -0.39
     fVar
    -0.32
    featureID
    -0.32
     invokingState
    -0.31
    ✭✭
    -0.30
     bay
    -0.29
     fér
    -0.29
    ねて
    -0.29
     Administrativna
    -0.28
     ferons
    -0.28
    POSITIVE LOGITS
     GenerationType
    0.66
    
    0.62
    InjectAttribute
    0.57
    attutto
    0.56
    ="@+
    0.54
    SequentialGroup
    0.54
    mainen
    0.53
    <?
    0.53
    ckså
    0.52
     CanadaChoose
    0.51
    Act Density 0.516%

    No Known Activations