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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Chaplin"

    oai_token-act-pair · gpt-3.5-turbo

    references to Charlie Chaplin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ACTION
    -0.76
    FORE
    -0.75
    PRES
    -0.74
    REAM
    -0.73
    å§
    -0.72
    ACTED
    -0.72
    lings
    -0.70
    PORT
    -0.69
    LEASE
    -0.69
    20439
    -0.68
    POSITIVE LOGITS
     Cha
    1.21
     cha
    1.15
    plin
    1.13
    isson
    1.08
    plain
    1.04
    ise
    0.88
    isen
    0.85
    isel
    0.84
    ussian
    0.84
    adian
    0.84
    Act Density 0.008%

    No Known Activations