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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or definitive statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Penh
    -0.52
    UrlResolution
    -0.50
    interview
    -0.47
    roek
    -0.46
    tagHelperRunner
    -0.46
     interview
    -0.44
    localctx
    -0.44
     Interview
    -0.44
    homo
    -0.44
    RuleContext
    -0.42
    POSITIVE LOGITS
     why
    0.57
     pretty
    0.50
     enough
    0.47
    Exactly
    0.46
     how
    0.45
     precisely
    0.42
     exactly
    0.42
     suficiente
    0.42
     EXACTLY
    0.39
     suficientes
    0.39
    Act Density 0.121%

    No Known Activations