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

    Neuronpedia

    INDEX
    Explanations

    unusual characters or sequences within text

    oai_token-act-pair · gpt-3.5-turbo

    ambiguous or generic statements that lack specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.92
    atis
    -0.69
    olicy
    -0.69
     estranged
    -0.68
     inactive
    -0.68
    emort
    -0.66
    ibrary
    -0.66
    arde
    -0.65
    ensibly
    -0.65
    uly
    -0.64
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    1.14
    ³³³³³³³³
    1.12
    ³³³³
    1.06
    Anyway
    1.05
    ³³³
    0.95
    ³³
    0.94
     Anyway
    0.90
    Anonymous
    0.90
    ONSORED
    0.87
    Posted
    0.86
    Act Density 0.418%

    No Known Activations