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

    Neuronpedia

    INDEX
    Explanations

    the presence of a special character or marker indicating a new section or theme

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to specific locations or entities named "White"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    cffffcc
    -0.92
    ategory
    -0.78
    udeau
    -0.77
    ANS
    -0.76
    ITAL
    -0.75
    Downloadha
    -0.75
    awaru
    -0.73
    APH
    -0.72
    yrinth
    -0.72
    REM
    -0.72
    POSITIVE LOGITS
    caps
    1.19
    horse
    1.11
     supremacist
    1.06
     Sox
    1.05
    hall
    1.03
    house
    1.00
    beard
    1.00
     supremacists
    0.97
    bread
    0.96
    head
    0.92
    Act Density 0.030%

    No Known Activations