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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparative language, particularly in the context of abundance or satisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lam
    -0.19
    ini
    -0.16
    386
    -0.14
     Fritz
    -0.14
    ours
    -0.14
     toll
    -0.14
    .DataAccess
    -0.13
    ê¼
    -0.13
    ermen
    -0.13
    _stderr
    -0.13
    POSITIVE LOGITS
     than
    0.55
    than
    0.45
    -than
    0.44
     Than
    0.40
     THAN
    0.39
    Than
    0.37
    _than
    0.34
     než
    0.30
     än
    0.29
     more
    0.26
    Act Density 0.019%

    No Known Activations