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

    Neuronpedia

    INDEX
    Explanations

    instances and descriptions of rarity or uncommonness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bender
    -0.74
     servici
    -0.69
     ruota
    -0.68
    odeon
    -0.64
     igenom
    -0.63
    bender
    -0.62
    ...');
    -0.59
     perasaan
    -0.59
    yafet
    -0.58
    mandala
    -0.58
    POSITIVE LOGITS
     rare
    2.28
     Rare
    2.13
    Rare
    2.05
     RARE
    1.97
    rare
    1.89
     rarer
    1.86
     rarity
    1.78
     rares
    1.78
     rarest
    1.69
     rara
    1.61
    Act Density 0.114%

    No Known Activations