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

    Neuronpedia

    INDEX
    Explanations

    words expressing inclusivity and totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rike
    -0.16
    дина
    -0.15
    stal
    -0.15
    ÑĢик
    -0.15
    aby
    -0.15
    ÑĮÑĤе
    -0.15
    daq
    -0.14
    ietet
    -0.14
    dale
    -0.13
    nets
    -0.13
    POSITIVE LOGITS
    errat
    0.17
    uding
    0.17
    ende
    0.16
    usive
    0.16
     gam
    0.15
    iles
    0.15
    ahi
    0.15
    igator
    0.15
    ah
    0.15
    uve
    0.15
    Act Density 0.095%

    No Known Activations