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

    Neuronpedia

    INDEX
    Explanations

    topics related to identity and representation in various social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '])){
    -0.65
    DeleteBehavior
    -0.65
     Efq
    -0.64
    ();)
    -0.63
    曖昧さ回避
    -0.60
     Mahomet
    -0.60
     gynnwys
    -0.60
    :]:
    -0.57
    ']))
    -0.56
     nutritive
    -0.54
    POSITIVE LOGITS
     identity
    0.87
    自己是
    0.75
    identity
    0.71
     szár
    0.71
     identitas
    0.67
     Identity
    0.67
    identification
    0.67
     ethnicity
    0.65
     identificação
    0.64
     identification
    0.64
    Act Density 0.532%

    No Known Activations