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

    Neuronpedia

    INDEX
    Explanations

    names of individuals being selected or hired for specific roles or positions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pauses
    -0.78
    grain
    -0.77
     glances
    -0.75
    artifacts
    -0.69
    gran
    -0.68
    tions
    -0.66
    browser
    -0.66
    pointers
    -0.64
    egg
    -0.62
    noticed
    -0.62
    POSITIVE LOGITS
     participate
    1.14
     join
    1.01
     defend
    1.00
     oversee
    1.00
     compensate
    0.99
     fulfill
    0.99
     provide
    0.98
     give
    0.97
     meet
    0.97
     negotiate
    0.97
    Act Density 0.216%

    No Known Activations