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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements expressed as percentages or weights

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.65
    antaine
    -0.64
    ParallelGroup
    -0.60
     snippetHide
    -0.60
    StartTag
    -0.59
    DockStyle
    -0.58
    tispiece
    -0.57
     TextAlign
    -0.55
    AssignableFrom
    -0.54
    Expedia
    -0.54
    POSITIVE LOGITS
    Personendaten
    0.55
    icat
    0.52
    ритори
    0.52
     PREC
    0.50
     too
    0.49
    uca
    0.48
    ArrowToggle
    0.48
    onomic
    0.48
    icale
    0.48
    multirow
    0.47
    Act Density 0.016%

    No Known Activations