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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or events that have been happening continuously over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of continuity or persistence over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aucus
    -0.71
    Enlarge
    -0.67
    Reviewed
    -0.64
    esses
    -0.58
    ĺħ
    -0.57
     Legions
    -0.56
    arity
    -0.56
    hemy
    -0.56
    uebl
    -0.55
    emis
    -0.55
    POSITIVE LOGITS
    green
    1.25
    thing
    1.17
    lasting
    1.07
    more
    1.03
    theless
    0.93
     since
    0.93
    since
    0.90
    present
    0.88
    THING
    0.83
    last
    0.81
    Act Density 0.033%

    No Known Activations