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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and contextually relevant phrases that indicate a narrative or conversational flow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.08
    3:0.05
    4:0.25
    5:0.03
    6:0.19
    7:0.07
    8:0.04
    9:0.03
    10:0.09
    11:0.08
    Negative Logits
    ナ
    -1.41
    ネ
    -1.29
     dating
    -1.27
     Sever
    -1.25
    ヴァ
    -1.23
    igham
    -1.19
    natal
    -1.18
    urance
    -1.18
     Cosmetic
    -1.16
     surfaces
    -1.15
    POSITIVE LOGITS
    rounder
    1.39
     indo
    1.38
    anwhile
    1.36
    jew
    1.35
    ophon
    1.34
    bart
    1.32
     surv
    1.31
    du
    1.30
     starve
    1.29
    ribly
    1.29
    Act Density 0.001%

    No Known Activations