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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "transition" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    action
    -0.20
    íĴ
    -0.17
    ek
    -0.15
    inson
    -0.15
    isl
    -0.14
    æł·çļĦ
    -0.14
    by
    -0.14
    emi
    -0.14
    uy
    -0.14
    atan
    -0.13
    POSITIVE LOGITS
    ary
    0.29
    /trans
    0.24
    ed
    0.24
    aries
    0.23
    ally
    0.19
    als
    0.19
     period
    0.19
    arily
    0.18
    nelle
    0.18
    -period
    0.18
    Act Density 0.018%

    No Known Activations