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

    Neuronpedia

    INDEX
    Explanations

    references to insiders or insider information

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

    insider knowledge, told, eyewitness testimony

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    เภ
    -0.46
     Ay
    -0.45
     FetchType
    -0.45
    LookAnd
    -0.45
    GenerationType
    -0.44
     toilets
    -0.43
     Tur
    -0.42
     RequestMethod
    -0.41
     furg
    -0.41
    Facades
    -0.41
    POSITIVE LOGITS
     insider
    2.13
     Insider
    1.91
    insider
    1.84
    Insider
    1.82
     insiders
    1.73
    inside
    0.89
    Inside
    0.87
     inside
    0.85
     Inside
    0.84
     INSIDE
    0.76
    Act Density 0.003%

    No Known Activations