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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to names, particularly those associated with individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.05
    3:0.43
    4:0.03
    5:0.02
    6:0.04
    7:0.14
    8:0.06
    9:0.05
    10:0.05
    11:0.04
    Negative Logits
    戦
    -1.40
    ELF
    -1.35
    �
    -1.31
    天
    -1.29
    生
    -1.29
    ラン
    -1.28
    Bir
    -1.27
    BUS
    -1.26
    �
    -1.25
    ドラゴン
    -1.25
    POSITIVE LOGITS
    ascript
    1.57
    naissance
    1.48
    kef
    1.41
    mony
    1.35
    earch
    1.35
    enegger
    1.34
     spons
    1.27
    spective
    1.27
    ndum
    1.26
    peat
    1.26
    Act Density 0.031%

    No Known Activations