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

    Neuronpedia

    INDEX
    Explanations

    names of cities and places

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate significant events or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     interven
    -0.79
    aterasu
    -0.78
    ieth
    -0.75
     Amen
    -0.75
     UNCLASSIFIED
    -0.69
     conscience
    -0.66
     wills
    -0.66
    onite
    -0.66
     :=
    -0.65
     Ibid
    -0.61
    POSITIVE LOGITS
    terday
    0.90
     understandably
    0.83
     unsurprisingly
    0.82
    ãĥĥãĥī
    0.82
     predictably
    0.81
     Turns
    0.78
    Yesterday
    0.77
    atform
    0.77
     congratulations
    0.76
     rightfully
    0.76
    Act Density 0.743%

    No Known Activations