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

    Neuronpedia

    INDEX
    Explanations

    the first-person singular pronoun

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    information regarding updates or progress reports

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to announcements or updates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.07
    3:0.08
    4:0.09
    5:0.08
    6:0.08
    7:0.07
    8:0.07
    9:0.08
    10:0.09
    11:0.07
    Negative Logits
    edia
    -1.68
    Loading
    -1.65
    ona
    -1.46
     WP
    -1.41
    upload
    -1.41
    lib
    -1.39
    xa
    -1.36
     Omar
    -1.33
    xd
    -1.32
    phony
    -1.32
    POSITIVE LOGITS
     nailed
    1.69
     teamed
    1.61
     circled
    1.56
     pioneered
    1.51
     mastered
    1.49
     redes
    1.47
     drilled
    1.46
     formulated
    1.46
     colle
    1.41
     transitioned
    1.41
    Act Density 0.000%

    No Known Activations