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

    Neuronpedia

    INDEX
    Explanations

    numeric values, particularly related to years and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivity
    -0.85
    ivities
    -0.85
    ique
    -0.84
    iques
    -0.81
    ãĤ¤ãĥĪ
    -0.74
    lier
    -0.74
    ional
    -0.72
    icles
    -0.72
    icular
    -0.68
    ically
    -0.67
    POSITIVE LOGITS
     externalToEVAOnly
    1.03
    98
    0.92
    989
    0.86
    58
    0.86
    987
    0.85
    765
    0.85
    mph
    0.84
    57
    0.83
    68
    0.83
    80
    0.82
    Act Density 0.055%

    No Known Activations