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

    Neuronpedia

    INDEX
    Explanations

    phrases regarding various motivations or justifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /run
    -0.15
    omp
    -0.15
    ole
    -0.14
    cat
    -0.13
    IRST
    -0.13
    gow
    -0.13
    coon
    -0.13
    oje
    -0.13
    oy
    -0.13
    cm
    -0.13
    POSITIVE LOGITS
     why
    0.20
    lessly
    0.18
    nant
    0.17
     dolayı
    0.16
    why
    0.16
    nal
    0.15
    ourke
    0.15
    nable
    0.15
     Reeves
    0.15
     reasons
    0.15
    Act Density 0.035%

    No Known Activations