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

    Neuronpedia

    INDEX
    Explanations

    the name "White"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "White."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ITAL
    -0.86
    ngth
    -0.81
    igslist
    -0.80
    ategory
    -0.78
    yrinth
    -0.78
    cffffcc
    -0.77
    itals
    -0.76
    itual
    -0.76
    rative
    -0.75
    =-=-=-=-
    -0.75
    POSITIVE LOGITS
    caps
    1.16
     supremacist
    1.10
    house
    1.09
    horn
    1.05
     supremacists
    1.02
    berry
    1.02
    horse
    1.01
     Sox
    0.99
    bread
    0.97
    houses
    0.96
    Act Density 0.025%

    No Known Activations