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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making bold statements or commitments

    oai_token-act-pair · gpt-3.5-turbo

    verbs and their derivatives related to taking or achieving something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ica
    -0.67
     Tub
    -0.66
     Scand
    -0.64
     Dahl
    -0.62
     Kills
    -0.61
    netflix
    -0.60
    tf
    -0.60
    aceae
    -0.59
    inian
    -0.58
    ifix
    -0.58
    POSITIVE LOGITS
    kered
    0.77
    geon
    0.68
     farewell
    0.67
     allegiance
    0.67
     concessions
    0.65
     away
    0.61
    ark
    0.61
     amounts
    0.61
    eteenth
    0.60
     Citiz
    0.60
    Act Density 0.076%

    No Known Activations