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

    Neuronpedia

    INDEX
    Explanations

    sections of text containing high activation or priority markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.49
    V
    -0.48
    ’
    -0.47
    -
    -0.45
    存于
    -0.45
     
    -0.44
    ,
    -0.44
    Z
    -0.42
    unii
    -0.41
    .
    -0.41
    POSITIVE LOGITS
    ScopeManager
    8.40
     Normdatei
    1.57
    AnchorStyles
    1.54
    ImageContext
    1.50
    ConstraintMaker
    1.38
     مشين
    1.34
    TagHelper
    1.34
    BeginContext
    1.34
    migrationBuilder
    1.31
    enumii
    1.30
    Act Density 0.002%

    No Known Activations