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

    Neuronpedia

    INDEX
    Explanations

    instances that are classified or referenced as "cases."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    +#+#
    -0.98
     AttributeSet
    -0.82
    ValueStyle
    -0.80
    fjspx
    -0.77
     TextAlign
    -0.76
     vertes
    -0.73
    LEncoder
    -0.71
     AppDelegate
    -0.71
    msgTypes
    -0.69
     وتسجيلات
    -0.69
    POSITIVE LOGITS
    ukone
    0.53
     a
    0.51
     przypadku
    0.50
    checs
    0.48
    会儿
    0.47
    若是
    0.47
    גון
    0.47
     kasarigan
    0.47
     Fisch
    0.46
    การ
    0.46
    Act Density 0.019%

    No Known Activations