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

    Neuronpedia

    INDEX
    Explanations

    dates or time periods indicated by hyphens

    oai_token-act-pair · gpt-3.5-turbo

    references to late-night shows or related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rica
    -0.75
     Shutterstock
    -0.74
     mirrors
    -0.70
     DOI
    -0.69
     brim
    -0.69
     Torch
    -0.67
     Ruler
    -0.66
     Griffin
    -0.65
     whist
    -0.64
     Ally
    -0.63
    POSITIVE LOGITS
    model
    1.22
    night
    1.18
    period
    1.13
    morning
    1.11
    mid
    1.11
    middle
    1.11
    earth
    1.10
    stage
    1.09
    breaking
    1.04
    term
    1.04
    Act Density 0.036%

    No Known Activations