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

    Neuronpedia

    INDEX
    Explanations

    positive sentiments or expressions of enjoyment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal preference or enjoyment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uthor
    -0.81
     transpired
    -0.70
    ailable
    -0.69
    pter
    -0.67
    river
    -0.66
     disadvantage
    -0.64
    imester
    -0.62
    clair
    -0.62
    ledged
    -0.61
    iseum
    -0.61
    POSITIVE LOGITS
     dearly
    0.89
     idea
    0.73
     scenery
    0.66
     crispy
    0.65
     guts
    0.65
     uncond
    0.64
     gravy
    0.62
     Flavoring
    0.62
     muff
    0.62
     spicy
    0.61
    Act Density 0.269%

    No Known Activations