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

    Neuronpedia

    INDEX
    Explanations

    references to vehicles or outdoor activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prat
    -0.15
    ionic
    -0.15
     straw
    -0.15
     colon
    -0.14
     Belt
    -0.14
    asz
    -0.14
     Straw
    -0.14
     Fey
    -0.13
    969
    -0.13
    968
    -0.13
    POSITIVE LOGITS
     rad
    0.28
    -rad
    0.21
     sick
    0.21
     filmer
    0.20
     Sick
    0.20
     dia
    0.20
    .rad
    0.19
     Stoke
    0.19
    (rad
    0.19
    Rad
    0.19
    Act Density 0.182%

    No Known Activations