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

    Neuronpedia

    INDEX
    Explanations

    instances of time-related phrases and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.05
    3:0.04
    4:0.08
    5:0.03
    6:0.46
    7:0.06
    8:0.03
    9:0.04
    10:0.06
    11:0.04
    Negative Logits
    ioxide
    -1.38
    elia
    -1.33
    obal
    -1.29
    eele
    -1.26
    olini
    -1.25
    inem
    -1.25
    udos
    -1.22
    emis
    -1.21
    UAL
    -1.21
    atto
    -1.20
    POSITIVE LOGITS
    mentioned
    1.57
    imester
    1.56
    enium
    1.51
    rences
    1.44
    nesday
    1.43
     awhile
    1.41
    rounder
    1.38
    ursday
    1.33
     NEC
    1.31
    eve
    1.30
    Act Density 0.048%

    No Known Activations