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

    Neuronpedia

    INDEX
    Explanations

    statements and phrases that convey general rules or principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.68
     next
    -0.59
    atiles
    -0.57
    CodeAttribute
    -0.56
    antation
    -0.54
    VersionUID
    -0.53
    appendChild
    -0.53
    yntaxException
    -0.53
    tyard
    -0.52
     VIDEOTAPE
    -0.52
    POSITIVE LOGITS
     generally
    1.15
    generally
    1.08
    Generally
    1.00
     Generally
    0.98
     generell
    0.94
    sätzlich
    0.89
     grundsätzlich
    0.83
     geral
    0.81
     generales
    0.81
     générale
    0.80
    Act Density 0.289%

    No Known Activations