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

    Neuronpedia

    INDEX
    Explanations

    references to "human."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Obrázky
    -0.83
     Diwali
    -0.75
     Trotz
    -0.74
     elétrica
    -0.73
     productivo
    -0.73
     isolado
    -0.72
    kulum
    -0.72
     againſt
    -0.71
     oxalate
    -0.70
     econômica
    -0.69
    POSITIVE LOGITS
     human
    1.58
     Human
    1.48
    human
    1.43
    Human
    1.42
     HUMAN
    1.41
    HUMAN
    1.40
     humans
    1.14
    uman
    1.09
     Humans
    1.07
    Humans
    1.00
    Act Density 0.062%

    No Known Activations