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

    Neuronpedia

    INDEX
    Explanations

    references to rarity or uncommon occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ruota
    -0.64
    odeon
    -0.61
     servici
    -0.60
     uParam
    -0.56
     Bender
    -0.56
    axel
    -0.56
    Bande
    -0.53
    署
    -0.53
     Milit
    -0.52
     dicendo
    -0.51
    POSITIVE LOGITS
     rare
    3.38
     Rare
    3.13
    Rare
    3.02
    rare
    2.86
     RARE
    2.77
     rarer
    2.55
     rarity
    2.51
     rares
    2.44
     rarest
    2.42
     rara
    2.16
    Act Density 0.070%

    No Known Activations