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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the act of performing tasks or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "perform" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shi
    -0.73
    brow
    -0.73
    fram
    -0.70
    wart
    -0.69
    raft
    -0.68
    ship
    -0.63
    cott
    -0.63
     Saur
    -0.62
    clad
    -0.61
    ixed
    -0.61
    POSITIVE LOGITS
     evaluations
    0.88
     abortions
    0.84
    ativity
    0.83
     err
    0.79
    ities
    0.79
     miracles
    0.79
     CPR
    0.78
    uate
    0.77
     renovations
    0.73
    acus
    0.72
    Act Density 0.030%

    No Known Activations