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

    Neuronpedia

    INDEX
    Explanations

    phrases signaling evidence and logical conclusions, particularly in terms of evaluating different types of evidence in arguments

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.66
    UnusedPrivate
    -0.62
    utnik
    -0.59
    PreferredItem
    -0.55
     Особенно
    -0.54
    apunov
    -0.52
     MatDialog
    -0.48
    SourceChecksum
    -0.48
     hoofd
    -0.47
    BufferException
    -0.46
    POSITIVE LOGITS
     respectively
    0.61
     autorytatywna
    0.57
    respectively
    0.57
    حوالہ
    0.56
    adaptiveStyles
    0.55
     Regu
    0.54
    pexpr
    0.53
    Gesch
    0.52
    ImageContext
    0.52
    ChildIndex
    0.51
    Act Density 0.321%

    No Known Activations