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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical properties and measures of uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical or technical terms related to precision, uniqueness, and performance metrics.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     flesta
    -0.48
     fleste
    -0.48
    PathVariable
    -0.46
    mlx
    -0.43
    Joint
    -0.42
    -
    -0.42
     Joint
    -0.41
    tagext
    -0.41
    Selected
    -0.40
     egna
    -0.40
    POSITIVE LOGITS
    veness
    1.02
    teness
    0.91
    queness
    0.89
    tiveness
    0.89
    ousness
    0.86
    yness
    0.85
    eness
    0.83
    lessness
    0.83
    ctiveness
    0.83
    siveness
    0.82
    Act Density 0.450%

    No Known Activations