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

    Neuronpedia

    INDEX
    Explanations

    positive and comparative evaluations of experiences or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AsUp
    -0.75
    bootstrapcdn
    -0.71
    انجليز
    -0.69
    lunda
    -0.59
    parsedMessage
    -0.56
    }{*}{}
    -0.55
     ویکی‌پدیای
    -0.55
    ſelves
    -0.54
     ویکی‌پدیا
    -0.54
     Vergangenheit
    -0.54
    POSITIVE LOGITS
     ever
    1.64
     EVER
    1.33
     Ever
    1.25
    ever
    1.19
    Ever
    1.16
     pernah
    0.99
    EVER
    0.97
     jamais
    0.93
     jemals
    0.80
     jamás
    0.71
    Act Density 0.096%

    No Known Activations