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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating alternative options or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     æº
    -0.07
    OLLOW
    -0.06
    emme
    -0.06
    Äĥn
    -0.06
    füh
    -0.06
    ND
    -0.06
    itte
    -0.06
     sy
    -0.06
    avern
    -0.06
     undes
    -0.06
    POSITIVE LOGITS
     why
    0.07
     how
    0.07
     Bust
    0.07
    ãĤ¹ãĤ¯
    0.07
    ılım
    0.07
    ator
    0.07
    à¤Łà¤¨
    0.07
     How
    0.07
    -how
    0.07
    HOW
    0.07
    Act Density 0.007%

    No Known Activations