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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a conclusion or summary in a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conclusions or final judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    href
    -0.74
    tan
    -0.72
    elight
    -0.72
    dos
    -0.72
    eni
    -0.70
    maid
    -0.66
    eners
    -0.66
    lot
    -0.64
    names
    -0.63
    corn
    -0.63
    POSITIVE LOGITS
     concluding
    0.84
    uations
    0.76
    igm
    0.73
     conclusion
    0.73
    ãĤ¤ãĥĪ
    0.69
     conclude
    0.67
    itutes
    0.67
     FANTASY
    0.67
    itute
    0.66
     conclusions
    0.66
    Act Density 0.035%

    No Known Activations