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

    Neuronpedia

    INDEX
    Explanations

    directives or prompts related to taking action and seeking additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    look at, find out, be careful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.50
    recated
    -0.43
    исленность
    -0.42
    Portale
    -0.41
    tı
    -0.40
    EndContext
    -0.39
    AtIndexPath
    -0.38
    INA
    -0.37
    TargetException
    -0.37
    Personendaten
    -0.36
    POSITIVE LOGITS
    GIVEREF
    0.54
    0.46
     оригіналу
    0.45
    WriteTagHelper
    0.43
     insertar
    0.40
     Efq
    0.40
    featureID
    0.40
     nargin
    0.40
     Surv
    0.40
     виправивши
    0.39
    Act Density 0.055%

    No Known Activations