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

    Neuronpedia

    INDEX
    Explanations

    phrases related to setting, starting, or initiating various actions or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of setting standards or achieving significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.78
    iors
    -0.76
    steen
    -0.69
    itely
    -0.69
    otten
    -0.66
    SB
    -0.65
    parts
    -0.62
     subt
    -0.61
    spell
    -0.61
     poured
    -0.61
    POSITIVE LOGITS
     precedent
    0.84
    ilts
    0.76
     abl
    0.75
     sails
    0.75
     loose
    0.70
     Ascend
    0.69
    eering
    0.69
    mberg
    0.68
     Sail
    0.67
    IK
    0.66
    Act Density 0.127%

    No Known Activations