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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "perform"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "perform" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inki
    -0.75
    issue
    -0.73
    ï¸ı
    -0.70
    ship
    -0.69
    rack
    -0.67
    raft
    -0.66
    cott
    -0.65
    liner
    -0.64
    wart
    -0.62
    esa
    -0.62
    POSITIVE LOGITS
     miracles
    1.03
     CPR
    0.93
     duties
    0.85
     poorly
    0.85
     abortions
    0.84
     tricks
    0.81
     stunts
    0.79
     satisf
    0.78
    ativity
    0.76
     onstage
    0.74
    Act Density 0.045%

    No Known Activations