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

    Neuronpedia

    INDEX
    Explanations

    phrases related to general topics or themes

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to generalizations and overall assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Eva
    -0.73
    rosso
    -0.71
    hots
    -0.71
    poon
    -0.70
     ashore
    -0.70
    ONSORED
    -0.69
    utics
    -0.68
    acus
    -0.67
    thood
    -0.66
    BIL
    -0.66
    POSITIVE LOGITS
     extent
    1.02
     portion
    0.97
     nature
    0.94
    most
    0.92
     assumption
    0.92
     population
    0.91
     populace
    0.90
    liest
    0.88
     equivalent
    0.88
     opposite
    0.88
    Act Density 0.233%

    No Known Activations