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

    Neuronpedia

    INDEX
    Explanations

    keywords related to events or activities like games, matches, seasons, and projects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports and entertainment events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idents
    -0.70
     Ones
    -0.68
     Empires
    -0.68
    tics
    -0.67
    efficients
    -0.64
    ernels
    -0.64
    urations
    -0.62
    unctions
    -0.61
    esters
    -0.61
    ails
    -0.60
    POSITIVE LOGITS
    wide
    0.75
    packed
    0.75
     reminiscent
    0.74
    itled
    0.74
    yssey
    0.74
    fitted
    0.73
    acious
    0.72
     resembling
    0.71
    istically
    0.70
     dubbed
    0.69
    Act Density 0.364%

    No Known Activations