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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistics and mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    овÑĭй
    -0.16
    adera
    -0.15
    ãĥ¥
    -0.15
     Mall
    -0.14
    abled
    -0.14
    onet
    -0.14
    ighter
    -0.14
    ÙĪار
    -0.14
    inh
    -0.14
    legal
    -0.14
    POSITIVE LOGITS
    ics
    0.42
    ICS
    0.33
    ika
    0.28
    atics
    0.28
    ÑģÑĤика
    0.27
    istics
    0.26
    rics
    0.26
    tics
    0.22
    ical
    0.22
    ика
    0.22
    Act Density 0.074%

    No Known Activations