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

    Neuronpedia

    INDEX
    Explanations

    variable word forms or suffixes that suggest modification or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xin
    -0.17
    ison
    -0.16
    abeth
    -0.15
    ached
    -0.15
     concern
    -0.14
    isp
    -0.14
    essa
    -0.14
    ئت
    -0.14
     unlike
    -0.14
    marks
    -0.13
    POSITIVE LOGITS
    beeld
    0.17
    -FIRST
    0.15
    atchewan
    0.15
    oppable
    0.15
    uggage
    0.14
     piger
    0.14
    ë§ŀ
    0.14
    bery
    0.14
    eldo
    0.14
    abic
    0.14
    Act Density 0.217%

    No Known Activations