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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating action or state with specific preceding context, such as 'sitting on', 'receiving', 'serving in'

    oai_token-act-pair · gpt-3.5-turbo

    gerund forms of verbs indicating active or repetitive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pg
    -0.79
    twitch
    -0.67
    vu
    -0.63
    ère
    -0.63
    inho
    -0.61
    atell
    -0.60
     translating
    -0.60
     translation
    -0.60
    DragonMagazine
    -0.60
    ogy
    -0.59
    POSITIVE LOGITS
    redients
    0.79
    ãĤ¢ãĥ«
    0.72
     Cobra
    0.63
    itially
    0.62
     constituents
    0.62
     engagements
    0.61
     oneself
    0.60
    phas
    0.60
     Rebell
    0.58
     Pengu
    0.57
    Act Density 0.135%

    No Known Activations