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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a specific location or context within a sentence

    oai_token-act-pair · gpt-3.5-turbo

    references to specific countries or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cheong
    -0.73
    azines
    -0.73
    bats
    -0.71
    enz
    -0.68
    Photos
    -0.68
    Chel
    -0.67
    che
    -0.66
    units
    -0.62
    KC
    -0.62
    phies
    -0.61
    POSITIVE LOGITS
     starved
    0.81
     plagued
    0.78
     populous
    0.73
     populated
    0.70
     burd
    0.70
     thri
    0.70
     dominated
    0.70
     hardly
    0.70
     ripe
    0.70
     staffed
    0.69
    Act Density 0.341%

    No Known Activations