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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming syntax and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsContent
    -0.80
    Diwedd
    -0.78
    WriteTagHelper
    -0.76
     تانيه
    -0.74
    tvguidetime
    -0.68
    NUMX
    -0.68
    WireFormatLite
    -0.68
    enterOuterAlt
    -0.65
     ExecuteAsync
    -0.65
     Lightboxes
    -0.65
    POSITIVE LOGITS
     etc
    0.75
    ↵↵
    0.60
    etc
    0.59
     and
    0.47
    .
    0.46
    ↵
    0.45
    [toxicity=0]
    0.45
    灌
    0.44
    espec
    0.44
    Amal
    0.44
    Act Density 0.354%

    No Known Activations