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

    Neuronpedia

    INDEX
    Explanations

    requests for information or action in a formal or professional context

    oai_token-act-pair · gpt-3.5-turbo

    terms related to making formal requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VERTISEMENT
    -0.79
    lasses
    -0.76
    nat
    -0.71
    phal
    -0.70
    urst
    -0.68
    olson
    -0.67
    Sax
    -0.66
     Rollins
    -0.65
     Barkley
    -0.65
    icals
    -0.65
    POSITIVE LOGITS
     permission
    1.17
     requests
    1.02
     forgiveness
    0.90
     pardon
    0.87
    Animation
    0.86
     requested
    0.85
     permissions
    0.83
     request
    0.83
     warrants
    0.79
     requ
    0.78
    Act Density 0.033%

    No Known Activations