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

    Neuronpedia

    INDEX
    Explanations

    instances of comparative and evaluative language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃĸL
    -0.15
    _marshall
    -0.15
     âĹĦ
    -0.14
    anny
    -0.14
    KHR
    -0.14
    gradable
    -0.14
    ÂĽ
    -0.14
    Cong
    -0.14
    oby
    -0.14
    abant
    -0.14
    POSITIVE LOGITS
     than
    0.44
    -than
    0.38
    than
    0.35
     THAN
    0.31
    _than
    0.29
     Than
    0.29
    Than
    0.28
     niż
    0.27
     än
    0.20
     než
    0.19
    Act Density 0.400%

    No Known Activations