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

    Neuronpedia

    INDEX
    Explanations

    occurrences of competitive events or matches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.11
    2:0.04
    3:0.05
    4:0.04
    5:0.03
    6:0.16
    7:0.04
    8:0.04
    9:0.25
    10:0.05
    11:0.09
    Negative Logits
    acid
    -3.87
     Lob
    -3.54
     Fleming
    -3.33
     amulet
    -3.25
    ead
    -3.22
    É
    -3.20
     Ballard
    -3.10
    Fle
    -3.09
     Barth
    -2.98
    ö
    -2.95
    POSITIVE LOGITS
     VS
    4.82
    VS
    4.47
    vs
    3.86
     Versus
    3.78
     versus
    3.64
    VG
    3.52
     watts
    3.30
     Vanguard
    3.26
     GTX
    3.21
    Bench
    3.20
    Act Density 0.001%

    No Known Activations