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

    Neuronpedia

    INDEX
    Explanations

    mentions of food items, specifically chocolates

    oai_token-act-pair · gpt-3.5-turbo

    references to chocolate and ITV

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILY
    -0.69
     Hutchinson
    -0.68
     Dunham
    -0.65
     crowd
    -0.62
     Hanson
    -0.62
    heit
    -0.61
     chick
    -0.60
    ^{
    -0.60
     Carlson
    -0.60
     Lum
    -0.58
    POSITIVE LOGITS
    onial
    1.09
    ocol
    0.97
    oric
    0.97
    ramid
    0.95
    odore
    0.91
    oire
    0.90
    oria
    0.90
     Seym
    0.90
    inia
    0.84
    unal
    0.84
    Act Density 0.024%

    No Known Activations