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
    1:0.01
    2:0.05
    3:0.05
    4:0.05
    5:0.04
    6:0.36
    7:0.15
    8:0.05
    9:0.06
    10:0.06
    11:0.04
    Negative Logits
    ruary
    -1.37
     unreliable
    -1.36
    pection
    -1.35
     specializing
    -1.34
     steroid
    -1.33
    geries
    -1.33
     reliable
    -1.32
     fart
    -1.29
     gimm
    -1.26
     lackluster
    -1.24
    POSITIVE LOGITS
    isen
    1.68
    �
    1.56
    Guard
    1.43
    icket
    1.43
    Jr
    1.38
    coins
    1.32
    ickets
    1.30
    AX
    1.30
     Rails
    1.30
    iak
    1.30
    Act Density 0.001%

    No Known Activations