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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with identity or identity verification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    بوابة
    -0.64
    ioutil
    -0.62
    indd
    -0.58
    VIAF
    -0.57
    SharedDtor
    -0.55
    AsUp
    -0.54
     vPvB
    -0.54
     Arquivado
    -0.54
    FunctionFlags
    -0.53
     باخ
    -0.53
    POSITIVE LOGITS
    section
    0.90
     monoxide
    0.68
    liminary
    0.57
     fø
    0.56
    żer
    0.56
     Damas
    0.56
     Bellini
    0.55
    ruptedException
    0.55
     Vlas
    0.54
     woodpecker
    0.54
    Act Density 0.005%

    No Known Activations