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

    Neuronpedia

    INDEX
    Explanations

    factual information and statistics related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oris
    -0.16
     pot
    -0.15
    arrow
    -0.15
    elsen
    -0.15
    llen
    -0.14
    adesh
    -0.14
    LEM
    -0.13
    esen
    -0.13
    liner
    -0.13
    hil
    -0.13
    POSITIVE LOGITS
    以ä¸Ĭ
    0.26
     ìĿ´ìĥģ
    0.22
     or
    0.21
     trợ
    0.18
    åıĬåħ¶
    0.16
    æĪĸèĢħ
    0.16
    loquent
    0.16
     hoặc
    0.16
     oder
    0.15
     minimum
    0.15
    Act Density 0.092%

    No Known Activations