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

    Neuronpedia

    INDEX
    Explanations

    comparative expressions related to numerical values or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eniable
    -0.17
    sWith
    -0.17
     overall
    -0.16
    phe
    -0.15
     more
    -0.15
     fewer
    -0.15
    itz
    -0.15
    rim
    -0.14
    ares
    -0.14
    eden
    -0.14
    POSITIVE LOGITS
     than
    0.44
    Than
    0.34
     Than
    0.33
    _than
    0.33
    than
    0.32
     THAN
    0.30
    äºİ
    0.29
     än
    0.25
    _THAN
    0.23
    æĸ¼
    0.23
    Act Density 0.060%

    No Known Activations