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

    Neuronpedia

    INDEX
    Explanations

    specific proper nouns and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.84
    PerformLayout
    -0.72
    LookAnd
    -0.66
    出版年
    -0.61
    NamedQueries
    -0.61
    afficheront
    -0.59
    gación
    -0.59
    AndEndTag
    -0.59
     propOrder
    -0.58
    ніципа
    -0.57
    POSITIVE LOGITS
     Blackboard
    0.55
    /***/
    0.54
    ctuaries
    0.53
     torches
    0.52
     seer
    0.52
    })));
    0.51
     swivel
    0.51
     Domes
    0.49
     graze
    0.49
     Theses
    0.49
    Act Density 0.877%

    No Known Activations