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

    Neuronpedia

    INDEX
    Explanations

    concepts and inquiries related to value assessments and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.76
    LabelTagHelper
    -0.75
     مشين
    -0.71
    EndContext
    -0.69
    談社
    -0.67
     pleaſure
    -0.66
     بيها
    -0.61
     przecież
    -0.61
     scorpion
    -0.61
    зулта
    -0.60
    POSITIVE LOGITS
    それとも
    0.75
     or
    0.68
    ?"
    0.58
     ?$
    0.57
     ogóle
    0.57
    ?*
    0.57
    有没有
    0.56
    ?:
    0.56
    ?'
    0.56
    msgSender
    0.54
    Act Density 0.548%

    No Known Activations