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

    Neuronpedia

    INDEX
    Explanations

    evaluative language indicating quality, particularly in the context of enjoyment and aesthetic appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.85
    較
    -0.69
    PerformLayout
    -0.69
    }))
    -0.67
     somewhat
    -0.66
    somewhat
    -0.66
     parseFrom
    -0.64
    ]]=
    -0.64
    SerializeField
    -0.64
    บ้าง
    -0.63
    POSITIVE LOGITS
     amazing
    0.82
     unbelievably
    0.79
     sekali
    0.77
    amazing
    0.77
     абсолютно
    0.75
     incredible
    0.74
    Huge
    0.74
    issime
    0.74
     brilliant
    0.73
     jamás
    0.72
    Act Density 1.803%

    No Known Activations