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

    Neuronpedia

    INDEX
    Explanations

    puzzling questions or uncertainties within a context

    oai_token-act-pair · gpt-3.5-turbo

    rhetorical questions throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    outine
    -0.74
    ulla
    -0.71
    bledon
    -0.67
    aper
    -0.66
    apers
    -0.63
    legate
    -0.63
    ened
    -0.63
     Nadu
    -0.61
    eper
    -0.61
     shortest
    -0.60
    POSITIVE LOGITS
     Nope
    1.20
     Yeah
    1.03
     Yep
    1.03
     Why
    1.00
     Seems
    0.99
    ¶
    0.96
     Yes
    0.95
     Surely
    0.95
     Maybe
    0.95
    ����
    0.89
    Act Density 0.072%

    No Known Activations