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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions related to announcements, promises, and notable events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.06
    2:0.14
    3:0.04
    4:0.01
    5:0.09
    6:0.11
    7:0.09
    8:0.16
    9:0.12
    10:0.06
    11:0.05
    Negative Logits
    …)
    -1.19
    )'
    -1.15
    !)
    -1.14
     Rolls
    -1.11
    MIT
    -1.10
    Smart
    -1.10
    !).
    -1.09
    MI
    -1.09
    MG
    -1.08
    Ranked
    -1.07
    POSITIVE LOGITS
    been
    1.40
    schild
    1.26
    etheus
    1.24
    ukong
    1.22
    vati
    1.18
    ihara
    1.18
    bara
    1.18
    anamo
    1.14
     Been
    1.13
    inez
    1.11
    Act Density 0.067%

    No Known Activations