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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and expressions indicating possibility or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.65
    ReusableCell
    -0.60
    cookieParser
    -0.57
     Gonna
    -0.55
    tgär
    -0.54
    InvalidProtocol
    -0.54
    InputLabel
    -0.53
     sauvages
    -0.53
     textStatus
    -0.52
    StructEnd
    -0.52
    POSITIVE LOGITS
     itself
    0.90
     themselves
    0.74
     well
    0.73
     herself
    0.69
    itself
    0.69
     in
    0.68
     Meksiku
    0.65
     here
    0.64
     thus
    0.62
     accordingly
    0.62
    Act Density 0.612%

    No Known Activations