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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and locations related to historical events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    olis
    -0.61
     Lemon
    -0.60
    atorium
    -0.59
     polic
    -0.58
    tein
    -0.58
    debian
    -0.57
    iscopal
    -0.56
    alky
    -0.55
    mand
    -0.55
     ASC
    -0.55
    POSITIVE LOGITS
    etc
    1.32
     etc
    0.97
    anything
    0.85
     assorted
    0.81
     latter
    0.79
     convol
    0.77
     shenan
    0.76
    whatever
    0.75
     myriad
    0.74
     prest
    0.74
    Act Density 0.393%

    No Known Activations