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

    Neuronpedia

    INDEX
    Explanations

    time schedules and routes

    oai_token-act-pair · gpt-3.5-turbo

    numerical sequences and their associated labels or routes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Icar
    -0.70
     Pax
    -0.65
     FY
    -0.65
     Calder
    -0.64
    Thumbnail
    -0.63
     Intent
    -0.62
    >[
    -0.60
     Gods
    -0.58
     property
    -0.57
     Christ
    -0.57
    POSITIVE LOGITS
    RN
    0.69
    forth
    0.68
    oslov
    0.67
    ARS
    0.67
    afety
    0.66
    tracks
    0.66
    nor
    0.65
    indal
    0.65
    enium
    0.64
    XL
    0.64
    Act Density 0.248%

    No Known Activations