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

    Neuronpedia

    INDEX
    Explanations

    elements related to complex character traits and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    labelledby
    -0.61
    StackNavigator
    -0.56
     Obtenez
    -0.54
     identité
    -0.50
    AndEndTag
    -0.50
    vantaged
    -0.49
     préférences
    -0.49
    ToBounds
    -0.48
    -0.47
    ForValue
    -0.47
    POSITIVE LOGITS
     unmatched
    1.12
     unheard
    1.12
     rarely
    1.11
     unimaginable
    1.08
     unparalleled
    1.07
     unknown
    1.07
     unprecedented
    1.06
     seldom
    1.06
     unseen
    1.02
     unthinkable
    1.02
    Act Density 0.890%

    No Known Activations