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

    Neuronpedia

    INDEX
    Explanations

    phrases related to principles or important elements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to tendencies or behaviors of groups and individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gallery
    -0.78
    icut
    -0.72
    batch
    -0.71
    wick
    -0.67
    selection
    -0.66
    sbm
    -0.65
    brow
    -0.64
    interface
    -0.64
    ascus
    -0.64
    bie
    -0.64
    POSITIVE LOGITS
    terness
    0.82
    imum
    0.78
    emonic
    0.78
    ercise
    0.77
     Aristotle
    0.72
    acious
    0.72
    arium
    0.70
    anism
    0.70
    manship
    0.70
    iveness
    0.67
    Act Density 0.155%

    No Known Activations