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

    Neuronpedia

    INDEX
    Explanations

    words related to promises and commitments

    oai_token-act-pair · gpt-3.5-turbo

    references to promises or commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Palmer
    -0.73
    lihood
    -0.71
    SEE
    -0.65
     needles
    -0.63
     Marino
    -0.63
    RESULTS
    -0.62
    gerald
    -0.61
     count
    -0.61
    ADRA
    -0.61
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
    POSITIVE LOGITS
    etheus
    1.30
    inently
    1.28
    otions
    1.27
    inent
    1.26
    otional
    1.23
    inence
    1.16
    ises
    1.12
    oter
    1.12
    otion
    1.01
    posal
    0.99
    Act Density 0.014%

    No Known Activations