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

    Neuronpedia

    INDEX
    Explanations

    expressions of comparison and metaphorical language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tois
    -0.48
    播
    -0.46
    指
    -0.46
    rpn
    -0.44
     định
    -0.44
     nhất
    -0.43
    สบ
    -0.43
    تمع
    -0.42
     P
    -0.42
    setAdapter
    -0.42
    POSITIVE LOGITS
    ModelAdmin
    0.77
     שוליים
    0.72
    ConstraintMaker
    0.70
    NameInMap
    0.68
    httphttps
    0.66
     مشين
    0.64
    SequentialGroup
    0.60
    __':
    0.59
    makeConstraints
    0.58
    ůj
    0.57
    Act Density 0.146%

    No Known Activations