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

    Neuronpedia

    INDEX
    Explanations

    technical or complex expressions related to data and computation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.05
    2:0.06
    3:0.02
    4:0.03
    5:0.03
    6:0.03
    7:0.08
    8:0.10
    9:0.05
    10:0.39
    11:0.06
    Negative Logits
     Hut
    -2.87
     Lep
    -2.78
    UFF
    -2.64
     Del
    -2.59
    yip
    -2.58
    atever
    -2.58
    ERAL
    -2.58
     evict
    -2.56
     Mald
    -2.53
     Pe
    -2.53
    POSITIVE LOGITS
     s
    9.10
     ss
    5.96
    s
    5.17
     S
    4.61
    ss
    4.45
    sb
    4.26
    S
    4.18
    sg
    3.69
     sd
    3.61
    sat
    3.45
    Act Density 0.143%

    No Known Activations