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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "perform"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    actions or tasks being performed by someone or something

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    shi
    -0.82
    raft
    -0.80
    fram
    -0.77
    brow
    -0.69
    wart
    -0.69
    ship
    -0.68
     Saur
    -0.64
    mes
    -0.64
    cube
    -0.63
    bour
    -0.62
    POSITIVE LOGITS
     evaluations
    0.95
     abortions
    0.89
     CPR
    0.83
    acus
    0.77
     renovations
    0.77
     miracles
    0.76
    inances
    0.75
    DAQ
    0.75
    ativity
    0.74
    ramids
    0.74
    Act Density 0.024%

    No Known Activations