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

    Neuronpedia

    INDEX
    Explanations

    French words

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific repeated symbol or character in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opian
    -0.69
    pex
    -0.68
     cryst
    -0.64
     livest
    -0.63
    nut
    -0.61
    userc
    -0.59
     blat
    -0.59
    aea
    -0.58
    oldown
    -0.58
    ixel
    -0.56
    POSITIVE LOGITS
    ————
    0.94
    ————————
    0.80
     Hear
    0.70
     Wrestling
    0.68
     Redux
    0.66
     Chapter
    0.65
     Written
    0.64
    Rat
    0.64
    feat
    0.63
     Rohingya
    0.63
    Act Density 0.074%

    No Known Activations