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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating comparisons or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dak
    -0.15
    å¹ķ
    -0.15
    )prepare
    -0.15
    ActionResult
    -0.15
    Ñĸдом
    -0.14
    ugh
    -0.14
    goo
    -0.14
     dissip
    -0.14
    IFO
    -0.14
    zos
    -0.14
    POSITIVE LOGITS
    fik
    0.17
    lying
    0.15
     наÑģ
    0.14
     Pier
    0.14
    atif
    0.14
    -schema
    0.13
    женеÑĢ
    0.13
    baum
    0.13
    rium
    0.13
     Mul
    0.13
    Act Density 0.107%

    No Known Activations