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

    Neuronpedia

    INDEX
    Explanations

    references to viewpoints or opinions within a discussion or article

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     busy
    -0.56
     en
    -0.56
    Unavailable
    -0.52
     mit
    -0.49
     som
    -0.47
     समीक्षाओं
    -0.47
     onto
    -0.47
    OUGH
    -0.46
     ne
    -0.46
    -
    -0.46
    POSITIVE LOGITS
    :✨
    1.08
    EDEFAULT
    0.83
    ſelves
    0.78
    اریخ
    0.72
    ſelf
    0.71
    berdayakan
    0.71
     Shakspeare
    0.70
    LEncoder
    0.66
    SBATCH
    0.65
     Majefty
    0.64
    Act Density 0.003%

    No Known Activations