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

    Neuronpedia

    INDEX
    Explanations

    verbs that imply some form of action or production

    oai_token-act-pair · gpt-3.5-turbo

    active verbs indicating actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.73
    adra
    -0.58
    iola
    -0.57
    MORE
    -0.55
    stood
    -0.55
    nesty
    -0.54
    fitting
    -0.54
    alore
    -0.54
    izable
    -0.53
    anca
    -0.52
    POSITIVE LOGITS
     aback
    0.80
    ream
    0.69
    river
    0.67
     )]
    0.67
    irect
    0.65
    Attempts
    0.61
    eals
    0.59
    monton
    0.59
     ]
    0.58
    own
    0.57
    Act Density 0.145%

    No Known Activations