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

    Neuronpedia

    INDEX
    Explanations

    strings or identifiers that appear to be related to coding, likely referencing variables or data types

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -1.27
     autorytatywna
    -1.16
     tartalomajánló
    -1.10
    EndGlobalSection
    -1.09
    存于互联网档案馆
    -1.06
     كومونز
    -1.05
     дописавши
    -1.05
     initComponents
    -1.05
     bezeichneter
    -1.05
     Audiodateien
    -1.04
    POSITIVE LOGITS
    7
    0.65
    3
    0.63
    .
    0.62
    4
    0.61
    9
    0.61
    8
    0.61
    1
    0.60
    2
    0.60
    6
    0.59
    ↵↵↵
    0.59
    Act Density 3.492%

    No Known Activations