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

    Neuronpedia

    INDEX
    Explanations

    words related to promises or commitments

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "promote."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fault
    -0.67
     mund
    -0.66
     wait
    -0.63
    SEE
    -0.61
     fashioned
    -0.60
     scissors
    -0.59
     screws
    -0.59
    Fine
    -0.58
    lihood
    -0.58
     bugs
    -0.57
    POSITIVE LOGITS
    etheus
    1.63
    otional
    1.52
    inent
    1.50
    otions
    1.47
    inently
    1.35
    oter
    1.31
    otion
    1.31
    oted
    1.29
    inence
    1.29
    ises
    1.29
    Act Density 0.017%

    No Known Activations