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

    Neuronpedia

    INDEX
    Explanations

    references to aviation and flight safety concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alen
    -0.15
    ramework
    -0.15
    olicit
    -0.15
    awei
    -0.15
    uye
    -0.15
    aven
    -0.14
     Fay
    -0.14
    odian
    -0.14
     Malk
    -0.14
    è»Ĭ
    -0.14
    POSITIVE LOGITS
     hang
    0.38
     Hang
    0.31
    Hang
    0.30
    hang
    0.29
     GA
    0.24
     Experimental
    0.23
     Fixed
    0.23
     hung
    0.23
     piston
    0.22
    åŀĤ
    0.22
    Act Density 0.083%

    No Known Activations