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

    Neuronpedia

    INDEX
    Explanations

    action words in imperative or declarative statements

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding intentions, ideas, or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iates
    -0.94
     pains
    -0.67
     Ago
    -0.65
     interven
    -0.65
    iate
    -0.65
    eor
    -0.64
    iating
    -0.63
     sides
    -0.61
    idences
    -0.61
    hens
    -0.61
    POSITIVE LOGITS
     moot
    0.81
    1001
    0.80
    olate
    0.74
     straightforward
    0.72
     spelled
    0.72
     based
    0.70
     priceless
    0.70
     probably
    0.69
     definitely
    0.69
     undoubtedly
    0.69
    Act Density 0.196%

    No Known Activations