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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "are" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AsUp
    -0.84
    posedge
    -0.74
    fromnode
    -0.73
     invokingState
    -0.72
    -0.71
     OnInit
    -0.71
     Poincar
    -0.70
     sebaliknya
    -0.70
     onPage
    -0.69
    Kjelder
    -0.69
    POSITIVE LOGITS
     many
    1.11
    Есть
    0.96
     few
    0.95
    many
    0.94
     MANY
    0.93
     numerous
    0.92
     Есть
    0.91
    MANY
    0.91
    Existen
    0.85
     fewer
    0.84
    Act Density 0.120%

    No Known Activations