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

    Neuronpedia

    INDEX
    Explanations

    keywords related to requests or inquiries

    oai_token-act-pair · gpt-3.5-turbo

    words and variations related to inquiries and requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fulness
    -0.75
    fully
    -0.68
     literally
    -0.67
    piece
    -0.66
     é
    -0.65
     polyg
    -0.63
     board
    -0.63
     overboard
    -0.62
     technically
    -0.61
     commonly
    -0.58
    POSITIVE LOGITS
    irement
    1.59
    isitions
    1.55
    iring
    1.52
    iries
    1.46
    ire
    1.41
    ired
    1.40
    isition
    1.38
    irements
    1.33
    ires
    1.30
    iration
    1.29
    Act Density 0.072%

    No Known Activations