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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical notations or notational conventions used in academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     singur
    -0.73
    등학교
    -0.72
     păr
    -0.70
     pracowników
    -0.70
     campana
    -0.69
    kommen
    -0.66
     ló
    -0.65
    RelativePath
    -0.65
     ścian
    -0.64
    moder
    -0.64
    POSITIVE LOGITS
    z
    1.22
    iz
    1.11
    zo
    1.11
     Lizzy
    1.09
    Kuz
    1.08
    zzz
    1.08
     Lizzie
    1.06
     SZ
    1.06
    rz
    1.06
     CZ
    1.06
    Act Density 1.600%

    No Known Activations