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

    Neuronpedia

    INDEX
    Explanations

    terms related to documentation and quality control processes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     виправивши
    -0.76
     saites
    -0.75
     فريبيس
    -0.73
     estekak
    -0.72
    TagMode
    -0.67
     SwitchCompat
    -0.66
    ymce
    -0.64
    hyrchwyd
    -0.62
    nologue
    -0.62
    TypedDataSet
    -0.61
    POSITIVE LOGITS
    ài
    0.51
     widths
    0.51
    Widths
    0.51
    addPreferredGap
    0.49
    帖最后由
    0.49
     raiſ
    0.48
    (!__
    0.48
    setViewportView
    0.47
     Theſe
    0.47
     reaſon
    0.46
    Act Density 0.720%

    No Known Activations