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

    Neuronpedia

    INDEX
    Explanations

    words or phrases with unusual characters

    oai_token-act-pair · gpt-3.5-turbo

    unconventional symbols or characters and their context in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unidentified
    -0.70
     attorney
    -0.67
     renewed
    -0.66
     targeted
    -0.65
     salv
    -0.64
     discredited
    -0.63
     fugitive
    -0.63
     aven
    -0.62
     advisory
    -0.62
     exerted
    -0.61
    POSITIVE LOGITS
    ï¸ı
    1.15
     Anyway
    1.14
    BUT
    1.12
    Therefore
    1.08
     Therefore
    1.07
    yet
    1.07
    So
    1.04
    ometimes
    1.04
    cause
    1.04
    so
    1.04
    Act Density 0.251%

    No Known Activations