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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or government-related matters

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong affirmations or definitive statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tink
    -0.73
     overth
    -0.72
     manoeuv
    -0.70
     estranged
    -0.70
     footing
    -0.64
     favoured
    -0.64
     ideal
    -0.63
    hement
    -0.62
     grouping
    -0.62
     Reincarnated
    -0.61
    POSITIVE LOGITS
    ³³³³
    1.18
    ³³³³³³³³³³³³³³³³
    1.06
    ³³³
    1.04
    ³³³³³³³³
    1.01
    ³³
    0.94
    Sah
    0.88
    Posted
    0.87
    Therefore
    0.86
    Oracle
    0.86
    Synopsis
    0.85
    Act Density 0.218%

    No Known Activations