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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating unprecedented or exceptional events and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kV
    -0.49
    amaño
    -0.49
    AccessorTable
    -0.47
     plagioclase
    -0.44
     Cassini
    -0.44
     Todas
    -0.42
    anjutan
    -0.41
    astéro
    -0.41
    #+#
    -0.41
     levi
    -0.41
    POSITIVE LOGITS
     للاسماء
    0.93
    precedented
    0.73
     unprecedented
    0.73
     ever
    0.73
     EVER
    0.72
    BeginInit
    0.71
    ever
    0.69
    AnchorStyles
    0.68
     ModelExpression
    0.68
    nessed
    0.68
    Act Density 0.167%

    No Known Activations