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

    Neuronpedia

    INDEX
    Explanations

    references to figures or visuals in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     viewDidLoad
    -0.62
    Figure
    -0.59
    list
    -0.55
    Билгалдахарш
    -0.54
    گ
    -0.52
    각주
    -0.52
    הערות
    -0.51
    gen
    -0.51
    gn
    -0.50
     MatDialog
    -0.50
    POSITIVE LOGITS
    %)$
    0.69
    енча
    0.69
    /$',
    0.69
    @[+][
    0.68
    ']")
    0.64
    OGND
    0.61
    AZZ
    0.61
    {{/
    0.61
    )]=
    0.60
    vanced
    0.59
    Act Density 0.012%

    No Known Activations