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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to social judgment and norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.79
     Efq
    -0.77
     ſeveral
    -0.75
     Jefus
    -0.75
    DoubleQuotes
    -0.75
    ViewFeatures
    -0.73
     Theſe
    -0.73
    Autoritní
    -0.73
     preſent
    -0.72
     himſelf
    -0.71
    POSITIVE LOGITS
     cioccolato
    0.51
    vertret
    0.44
     اج
    0.43
     SwitchCompat
    0.43
    CDCl
    0.43
     unto
    0.43
     to
    0.42
    駛
    0.41
    adog
    0.40
    indak
    0.40
    Act Density 0.200%

    No Known Activations