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

    Neuronpedia

    INDEX
    Explanations

    verbs related to action or change

    oai_token-act-pair · gpt-3.5-turbo

    action-oriented verbs that indicate proposals, changes, and assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thing
    -0.67
    zo
    -0.64
     Ce
    -0.62
    tre
    -0.62
     Acquisition
    -0.58
     Ascension
    -0.57
    lord
    -0.55
     Type
    -0.55
     conqu
    -0.55
    ozo
    -0.55
    POSITIVE LOGITS
    arnaev
    0.87
    atform
    0.84
    irtual
    0.83
    ometimes
    0.82
    hement
    0.79
    jri
    0.79
    Ĥª
    0.78
    undown
    0.78
    ĵĺ
    0.77
    uggest
    0.75
    Act Density 0.272%

    No Known Activations