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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating separation or distinction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ush
    -0.16
    abras
    -0.16
     Ying
    -0.15
    incare
    -0.15
    owitz
    -0.14
    AZY
    -0.14
    .Resolve
    -0.14
     sah
    -0.13
    IRC
    -0.13
    tober
    -0.13
    POSITIVE LOGITS
    ÑĨов
    0.16
    resco
    0.16
    anship
    0.15
    orgia
    0.15
    addock
    0.14
    olla
    0.14
     Bout
    0.14
    edicine
    0.14
    âķĿ
    0.14
    egl
    0.14
    Act Density 0.024%

    No Known Activations