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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or actions coming to an end

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating closure or endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nda
    -0.65
     candid
    -0.64
    express
    -0.60
     prizes
    -0.60
    anges
    -0.59
     labels
    -0.58
    leading
    -0.58
     knowledgeable
    -0.57
     Regions
    -0.57
    reason
    -0.57
    POSITIVE LOGITS
     lately
    0.76
    bos
    0.73
     amid
    0.73
     halfway
    0.70
    ç
    0.68
    Ñĭ
    0.68
    ãĥ¼ãĥĨ
    0.66
    IER
    0.66
    ÃĽ
    0.65
     midway
    0.63
    Act Density 0.198%

    No Known Activations