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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of emergence or emerging phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åĪ»
    -0.16
    ra
    -0.15
    .sam
    -0.15
    atura
    -0.14
    tha
    -0.14
    ган
    -0.14
    mÄ±ÅŁ
    -0.14
    mes
    -0.14
    ãĤ«ãĥ¼
    -0.14
    ners
    -0.14
    POSITIVE LOGITS
     victorious
    0.26
     into
    0.18
     onto
    0.16
     from
    0.15
    -from
    0.15
     vict
    0.15
     trium
    0.15
     leaders
    0.15
    iah
    0.15
    USTER
    0.15
    Act Density 0.014%

    No Known Activations