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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to specific locations or names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.09
    3:0.03
    4:0.04
    5:0.07
    6:0.07
    7:0.03
    8:0.02
    9:0.03
    10:0.38
    11:0.03
    Negative Logits
    olt
    -2.73
    arter
    -2.63
    ort
    -2.59
    iety
    -2.43
    ollower
    -2.39
    BG
    -2.22
    OHN
    -2.21
    raham
    -2.18
    inate
    -2.13
    ari
    -2.11
    POSITIVE LOGITS
     McM
    3.39
     McKay
    2.70
     labou
    2.13
     Mia
    2.12
     Kush
    2.12
     dish
    2.11
     Umb
    2.09
     Cly
    2.09
     McKenzie
    2.06
     Paula
    2.06
    Act Density 0.000%

    No Known Activations