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

    Neuronpedia

    INDEX
    Explanations

    phrases related to complex social issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    FORE
    -0.83
     Millennium
    -0.68
     Rabbit
    -0.67
     Reich
    -0.66
     Pew
    -0.62
     Opposition
    -0.60
    bek
    -0.60
    hyde
    -0.60
    TPPStreamerBot
    -0.59
    )=(
    -0.58
    POSITIVE LOGITS
    endium
    1.46
    ulsive
    1.30
    artments
    1.22
    ilers
    1.22
    ounding
    1.12
    Lex
    1.04
    otent
    1.04
    ressing
    1.03
    ressive
    1.02
    oses
    1.00
    Act Density 0.010%

    No Known Activations