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

    Neuronpedia

    INDEX
    Explanations

    words related to accountability and the consequences of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    find
    -0.40
    ung
    -0.39
    Claw
    -0.38
    羹
    -0.37
     accanto
    -0.37
    j
    -0.36
     Klassen
    -0.36
    ్య
    -0.36
     so
    -0.36
    Ugly
    -0.35
    POSITIVE LOGITS
     >=",
    0.99
     ModelExpression
    0.99
     CreateTagHelper
    0.98
    TypedDataSet
    0.97
    хьтан
    0.90
    ValueStyle
    0.88
    Personendaten
    0.88
     <=",
    0.86
    Personensuche
    0.86
    thâu
    0.85
    Act Density 0.320%

    No Known Activations