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

    Neuronpedia

    INDEX
    Explanations

    emphasized positive attributes or qualities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tridge
    -0.18
    cean
    -0.17
    èĸĦ
    -0.15
    otropic
    -0.15
    usu
    -0.14
    atorial
    -0.14
    alles
    -0.14
    bsolute
    -0.14
    istani
    -0.14
    deme
    -0.14
    POSITIVE LOGITS
    holds
    0.19
    (er
    0.18
     enough
    0.18
    -strong
    0.17
    /power
    0.16
    /fast
    0.16
    strong
    0.16
    ening
    0.16
     strong
    0.16
    347
    0.15
    Act Density 0.035%

    No Known Activations