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

    Neuronpedia

    INDEX
    Explanations

    syntax related to programming structures and data definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mr
    -0.46
     we
    -0.44
    ju
    -0.42
    .
    -0.42
    no
    -0.41
    ...
    -0.40
    Mr
    -0.39
    ног
    -0.39
    h
    -0.39
     check
    -0.38
    POSITIVE LOGITS
     Paglinawan
    1.01
     ModelExpression
    0.90
     Савезне
    0.89
    VIAF
    0.86
    rrggbb
    0.85
     lenker
    0.84
     nakalista
    0.84
    +#+#
    0.82
    vember
    0.80
     tartalomajánló
    0.79
    Act Density 0.393%

    No Known Activations