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

    Neuronpedia

    INDEX
    Explanations

    words related to numbers or numerical expressions

    oai_token-act-pair · gpt-3.5-turbo

    numerical data presented in a "X percent" format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AVG
    -0.76
    ãĤ¯
    -0.75
    ãĥ£
    -0.74
    ãĤ¡
    -0.72
     Aether
    -0.71
    HCR
    -0.68
    achu
    -0.67
     Duo
    -0.67
    rawdownloadcloneembedreportprint
    -0.67
     Fiesta
    -0.67
    POSITIVE LOGITS
    eight
    1.16
    percent
    1.15
    six
    1.11
    five
    1.08
    year
    1.08
    seven
    1.07
    four
    1.07
    nine
    1.04
    second
    1.04
    two
    1.03
    Act Density 0.040%

    No Known Activations