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

    Neuronpedia

    INDEX
    Explanations

    specific instances of significant actions, qualities, and attributes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wan
    -0.15
    riet
    -0.15
     Knife
    -0.14
    ands
    -0.14
    Knife
    -0.14
     Corner
    -0.13
    ochen
    -0.13
    scoped
    -0.13
    linear
    -0.13
    wart
    -0.13
    POSITIVE LOGITS
    olec
    0.16
    DataExchange
    0.16
    elah
    0.15
    .pretty
    0.15
    iks
    0.14
     Dragons
    0.14
     Holl
    0.14
     Bram
    0.14
     Ðĵолов
    0.14
    venta
    0.14
    Act Density 0.015%

    No Known Activations