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

    Neuronpedia

    INDEX
    Explanations

    instances where someone continues speaking or providing information after an initial statement or question

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "went on," indicating a focus on ongoing actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UTF
    -0.71
    OTS
    -0.69
    Pokémon
    -0.68
    OTH
    -0.68
    BUT
    -0.66
    Enlarge
    -0.64
    Cod
    -0.64
    PORT
    -0.63
    Types
    -0.63
     charms
    -0.63
    POSITIVE LOGITS
    stage
    0.95
    Downloadha
    0.87
     hiatus
    0.83
     sale
    0.83
     stage
    0.79
     display
    0.76
     patrol
    0.75
    shore
    0.74
    sale
    0.74
    ibaba
    0.73
    Act Density 0.038%

    No Known Activations