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

    Neuronpedia

    INDEX
    Explanations

    terms related to product exclusions and warranty details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ейÑģÑĤв
    -0.15
    ót
    -0.15
    Ŀ
    -0.15
    aran
    -0.15
    stroy
    -0.15
     drop
    -0.15
    506
    -0.14
    uentes
    -0.14
     trick
    -0.14
    atro
    -0.14
    POSITIVE LOGITS
    ocument
    0.15
    ille
    0.14
    may
    0.14
    .prod
    0.14
    à¥įण
    0.14
    Limits
    0.14
    ise
    0.13
    erville
    0.13
    eln
    0.13
     Kelley
    0.13
    Act Density 0.059%

    No Known Activations