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

    Neuronpedia

    INDEX
    Explanations

    names of prominent individuals, particularly in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.04
    2:0.16
    3:0.16
    4:0.02
    5:0.02
    6:0.09
    7:0.08
    8:0.06
    9:0.10
    10:0.07
    11:0.13
    Negative Logits
    nikov
    -1.41
    merga
    -1.26
    anwhile
    -1.22
    conserv
    -1.20
    orks
    -1.15
    avering
    -1.12
    TPS
    -1.11
    orah
    -1.08
    defense
    -1.07
    bara
    -1.06
    POSITIVE LOGITS
     Ramos
    1.16
     Kemp
    1.15
     Became
    1.14
     Cummings
    1.09
     Rollins
    1.09
     Jonas
    1.09
     Hamm
    1.06
     Robinson
    1.02
    zos
    1.02
    iac
    1.01
    Act Density 0.007%

    No Known Activations