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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "flush" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "flush" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourke
    -0.78
    ramer
    -0.76
    yers
    -0.74
    ordan
    -0.73
    anwhile
    -0.72
    ean
    -0.68
    umer
    -0.67
    pheus
    -0.66
    rum
    -0.65
    nesota
    -0.64
    POSITIVE LOGITS
     flush
    1.27
     flushed
    1.04
    idious
    0.82
     toilets
    0.82
    ishable
    0.76
    uates
    0.72
     Throne
    0.71
    idding
    0.70
    uation
    0.69
    flush
    0.68
    Act Density 0.013%

    No Known Activations