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

    Neuronpedia

    INDEX
    Explanations

    references to legal actions or claims

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     OnInit
    -0.68
    "]]
    -0.65
     Witkin
    -0.59
    AutoField
    -0.58
    ⓧ
    -0.58
     ActivatedRoute
    -0.58
    \}\\
    -0.57
    ChildScrollView
    -0.56
    ']>
    -0.54
    styleUrls
    -0.54
    POSITIVE LOGITS
     indeed
    0.77
     таки
    0.75
    确实
    0.68
    的确
    0.67
    确实是
    0.64
     כן
    0.64
    #
    0.64
    確實
    0.63
     inderdaad
    0.62
    erdings
    0.60
    Act Density 0.153%

    No Known Activations