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

    Neuronpedia

    INDEX
    Explanations

    references to slugs and snails

    oai_token-act-pair · gpt-3.5-turbo

    references to slugs and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mental
    -0.70
     Scotia
    -0.70
    lesiastical
    -0.66
    foreseen
    -0.65
     Citizens
    -0.64
     Clin
    -0.63
    raising
    -0.62
    rogens
    -0.62
     Passage
    -0.61
    rians
    -0.61
    POSITIVE LOGITS
     slug
    1.20
     Slug
    1.14
    gers
    0.99
    ging
    0.90
    gery
    0.89
    bats
    0.85
    ger
    0.85
    ged
    0.81
    zag
    0.79
    atoon
    0.77
    Act Density 0.007%

    No Known Activations