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

    Neuronpedia

    INDEX
    Explanations

    strong emphasis on existence or presence, particularly using the word "are."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    QMetaType
    -0.69
    compos
    -0.65
    ngOnInit
    -0.64
     weevil
    -0.64
     neuem
    -0.62
     OnInit
    -0.59
    vänt
    -0.59
     BIL
    -0.59
    zieży
    -0.58
     useRouter
    -0.57
    POSITIVE LOGITS
     many
    1.14
     few
    1.11
     numerous
    1.08
    MANY
    1.06
     MANY
    1.06
    many
    0.98
     myriad
    0.95
     fewer
    0.92
     fewest
    0.91
     innumerable
    0.91
    Act Density 0.113%

    No Known Activations