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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating perceptions of simplicity and complexity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.66
     فريبيس
    -0.65
    ]--;
    -0.65
    @[
    -0.63
    '],$
    -0.63
    AutoScale
    -0.62
    bootstrapcdn
    -0.60
    ']],
    -0.59
     Ela
    -0.59
     Keane
    -0.58
    POSITIVE LOGITS
     partenza
    0.67
     chré
    0.65
    easy
    0.64
    avyzd
    0.64
     armé
    0.63
     prisonniers
    0.61
     drôle
    0.61
    tagHelperRunner
    0.61
     culturelles
    0.61
     suprême
    0.60
    Act Density 0.022%

    No Known Activations