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

    Neuronpedia

    INDEX
    Explanations

    phrases related to non-profit entities

    oai_token-act-pair · gpt-3.5-turbo

    references to non-profit organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tycoon
    -0.94
     Grind
    -0.71
     Showdown
    -0.69
    IUM
    -0.67
     guts
    -0.66
     Grill
    -0.65
     McGee
    -0.64
     Oaks
    -0.64
     Spoon
    -0.64
     trove
    -0.63
    POSITIVE LOGITS
    chal
    1.33
    linear
    1.29
    etheless
    1.27
    stop
    1.21
    verbal
    1.21
    lethal
    1.21
    profit
    1.14
    compliance
    1.13
    technical
    1.12
    fiction
    1.11
    Act Density 0.036%

    No Known Activations