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

    Neuronpedia

    INDEX
    Explanations

    votes against specific proposals or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of voting or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.84
    assic
    -0.78
    gallery
    -0.76
    hower
    -0.75
    operated
    -0.75
    hops
    -0.75
    overed
    -0.75
    ancial
    -0.72
    metry
    -0.69
    negie
    -0.68
    POSITIVE LOGITS
     worsh
    0.80
     wasting
    0.78
     anybody
    0.77
     accepting
    0.76
     prejudice
    0.74
     trusting
    0.73
     homosexuality
    0.72
     anyone
    0.71
     independence
    0.71
     upholding
    0.71
    Act Density 0.044%

    No Known Activations