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

    Neuronpedia

    INDEX
    Explanations

    locations or places indicated by "Nav" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to navigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fertil
    -0.67
     Pigs
    -0.65
    FORE
    -0.64
    rics
    -0.63
     retard
    -0.62
     bearer
    -0.62
    eger
    -0.61
     fide
    -0.59
     contraception
    -0.56
     è£ı
    -0.56
    POSITIVE LOGITS
    igator
    1.24
    igating
    1.19
    arro
    1.16
    igation
    1.13
    igate
    1.11
    igators
    1.11
    ajo
    1.11
    arre
    0.97
    istar
    0.93
    arette
    0.88
    Act Density 0.050%

    No Known Activations