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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a requirement or obligation

    oai_token-act-pair · gpt-3.5-turbo

    infinitive forms of verbs indicating actions or tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anchester
    -0.63
    videos
    -0.61
    DragonMagazine
    -0.59
    prison
    -0.56
    ighed
    -0.55
    fect
    -0.55
     cess
    -0.54
    reflect
    -0.54
    hide
    -0.53
    afety
    -0.53
    POSITIVE LOGITS
     done
    1.38
     do
    1.37
     doing
    1.31
     did
    1.19
     Doing
    1.17
     accomplish
    1.12
     accomplished
    1.05
    doing
    1.05
     does
    1.04
    do
    1.00
    Act Density 0.613%

    No Known Activations