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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negation or exclusion

    oai_token-act-pair · gpt-3.5-turbo

    references to non-governmental organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brus
    -0.86
     Led
    -0.78
     Bam
    -0.75
     Royale
    -0.74
     Barron
    -0.73
     Grill
    -0.73
     Zup
    -0.71
     Dickinson
    -0.71
     Butt
    -0.70
     Maze
    -0.70
    POSITIVE LOGITS
    existent
    1.76
    profit
    1.47
    linear
    1.27
    zero
    1.26
    functional
    1.25
    union
    1.23
    profits
    1.23
    governmental
    1.22
    violent
    1.22
    technical
    1.21
    Act Density 0.034%

    No Known Activations