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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.90
    ⓧ
    -0.85
     GenerationType
    -0.82
     resourceCulture
    -0.81
    AutoField
    -0.81
    BASEPATH
    -0.77
    addCriterion
    -0.75
    nonatomic
    -0.72
    SourceChecksum
    -0.71
     nonatomic
    -0.71
    POSITIVE LOGITS
     Sonder
    0.47
     thre
    0.45
    веду
    0.45
    ARSE
    0.45
    ienced
    0.45
     Cant
    0.44
     lauf
    0.43
     lost
    0.43
    Raw
    0.42
    juin
    0.42
    Act Density 0.266%

    No Known Activations