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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating forward-looking statements related to business plans or projections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.87
    StructEnd
    -0.87
     jadx
    -0.78
    RTGC
    -0.78
    awtextra
    -0.77
    addCriterion
    -0.76
    NewUrlParser
    -0.74
     مشين
    -0.74
    évaluateur
    -0.72
    featureID
    -0.71
    POSITIVE LOGITS
    ly
    0.69
    er
    0.68
    robe
    0.67
    looking
    0.63
    }{*}{
    0.62
    ward
    0.61
    wards
    0.61
    facing
    0.60
    ER
    0.59
    ness
    0.57
    Act Density 0.119%

    No Known Activations