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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names related to White

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffffcc
    -0.86
    ITAL
    -0.85
    Downloadha
    -0.80
    udeau
    -0.78
    ategory
    -0.76
    awaru
    -0.75
    yrinth
    -0.75
    odcast
    -0.74
    PsyNetMessage
    -0.73
    INGTON
    -0.71
    POSITIVE LOGITS
    caps
    1.12
    house
    1.11
    horse
    1.08
    beard
    1.07
     Sox
    1.06
     supremacist
    1.04
    hall
    1.03
    bread
    1.03
     supremacists
    1.01
    houses
    1.00
    Act Density 0.027%

    No Known Activations