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

    Neuronpedia

    INDEX
    Explanations

    specific technical terminology or jargon related to sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.07
    2:0.09
    3:0.07
    4:0.09
    5:0.07
    6:0.06
    7:0.10
    8:0.07
    9:0.08
    10:0.09
    11:0.08
    Negative Logits
     alarms
    -2.64
     notices
    -2.41
     noises
    -2.37
     complaints
    -2.35
     warnings
    -2.34
     statistics
    -2.29
     alerts
    -2.27
     leaks
    -2.22
     signs
    -2.20
     bug
    -2.19
    POSITIVE LOGITS
    arat
    2.85
    apolis
    2.67
    raltar
    2.62
     Adin
    2.62
     Seym
    2.57
     Volunte
    2.55
    owa
    2.35
    unicip
    2.30
    anie
    2.29
    eneg
    2.21
    Act Density 0.000%

    No Known Activations