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

    Neuronpedia

    INDEX
    Explanations

    names mentioned in text along with related descriptions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'L'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     democracy
    -0.70
     deterrent
    -0.65
     relevance
    -0.64
     behaviour
    -0.64
     deterrence
    -0.63
     Sud
    -0.63
     disadvant
    -0.62
     consequential
    -0.62
     fruitful
    -0.62
    uyomi
    -0.60
    POSITIVE LOGITS
    ï¸ı
    1.20
    agree
    0.81
    hole
    0.80
    dro
    0.78
    treated
    0.76
    felt
    0.76
    ï¸
    0.75
    wrote
    0.74
    iced
    0.74
    cre
    0.73
    Act Density 0.351%

    No Known Activations