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

    Neuronpedia

    INDEX
    Explanations

    specific types and conditions in code logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     downstream
    -0.15
     upstream
    -0.15
    erti
    -0.14
     Riverside
    -0.14
     Willow
    -0.14
    streams
    -0.14
    ipple
    -0.14
    umper
    -0.14
    Vault
    -0.14
    stream
    -0.13
    POSITIVE LOGITS
    rones
    0.17
    ical
    0.15
    istas
    0.14
    åŁ
    0.14
     cham
    0.14
    flate
    0.14
    Å¡ek
    0.14
    ICAL
    0.14
    eking
    0.14
    andal
    0.14
    Act Density 0.049%

    No Known Activations