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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.04
    3:0.05
    4:0.04
    5:0.04
    6:0.37
    7:0.12
    8:0.05
    9:0.07
    10:0.05
    11:0.04
    Negative Logits
    entially
    -1.31
    uously
    -1.19
     AST
    -1.17
     Fas
    -1.16
    KT
    -1.13
     depend
    -1.13
    FU
    -1.12
    cific
    -1.11
     Healer
    -1.10
    ruary
    -1.10
    POSITIVE LOGITS
    roth
    1.69
    zan
    1.47
    zon
    1.45
    acher
    1.43
    backer
    1.36
    adiq
    1.24
    cler
    1.23
    termination
    1.23
    itans
    1.23
    sche
    1.23
    Act Density 0.007%

    No Known Activations