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

    Neuronpedia

    INDEX
    Explanations

    quotations

    oai_token-act-pair · gpt-3.5-turbo

    quotations or dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sway
    -0.78
     adjud
    -0.74
     adv
    -0.72
     slam
    -0.70
     periodic
    -0.70
     favor
    -0.70
     scheduled
    -0.69
     favored
    -0.68
     inund
    -0.68
     bud
    -0.68
    POSITIVE LOGITS
    They
    1.21
    Whereas
    1.21
    It
    1.21
    We
    1.19
    Because
    1.18
    Especially
    1.18
    Hopefully
    1.17
    Otherwise
    1.16
    Nobody
    1.16
    There
    1.15
    Act Density 0.075%

    No Known Activations