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

    Neuronpedia

    INDEX
    Explanations

    statements prompting the reader to find or discover more information

    oai_token-act-pair · gpt-3.5-turbo

    phrases or calls to action related to discovery or seeking information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pered
    -0.72
    bara
    -0.71
    perty
    -0.68
     horm
    -0.65
    mph
    -0.64
     fracturing
    -0.63
    oiler
    -0.63
    istry
    -0.63
     paced
    -0.62
    itent
    -0.61
    POSITIVE LOGITS
    imon
    0.86
    ById
    0.84
    ings
    0.78
    ãĤ¤ãĥĪ
    0.77
    iveness
    0.77
    ãĤ¿
    0.76
    ãĤ¤
    0.76
    emouth
    0.74
    uments
    0.73
     Wond
    0.71
    Act Density 0.035%

    No Known Activations