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

    Neuronpedia

    INDEX
    Explanations

    descriptions of events or gatherings

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

    specific phrases and references related to meetings and discussions in media contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.16
    3:0.06
    4:0.24
    5:0.05
    6:0.03
    7:0.01
    8:0.14
    9:0.13
    10:0.04
    11:0.02
    Negative Logits
     absorbing
    -1.46
    chlor
    -1.40
    insured
    -1.30
    nor
    -1.27
     barley
    -1.23
     absorb
    -1.23
    utils
    -1.23
    erved
    -1.22
     maize
    -1.22
    ulo
    -1.22
    POSITIVE LOGITS
    ────
    1.45
    ゴン
    1.39
    Keefe
    1.38
     Commander
    1.36
    aucuses
    1.32
    OTOS
    1.32
     Bride
    1.31
     Oval
    1.30
    Interstitial
    1.30
     Ends
    1.29
    Act Density 0.002%

    No Known Activations