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

    Neuronpedia

    INDEX
    Explanations

    locations or settings

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and the preposition "in"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tropical
    -0.72
     pestic
    -0.70
     Leilan
    -0.67
     Micha
    -0.64
    estyles
    -0.63
     Stard
    -0.63
     toile
    -0.63
     tomat
    -0.61
    utsu
    -0.61
     Bounce
    -0.61
    POSITIVE LOGITS
    enhagen
    0.73
    xon
    0.71
    acle
    0.71
    cel
    0.64
    readable
    0.64
    psey
    0.64
    mingham
    0.64
    xit
    0.62
    malink
    0.62
    pire
    0.61
    Act Density 0.000%

    No Known Activations