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

    Neuronpedia

    INDEX
    Explanations

    references to locations or directions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sterling
    -0.68
    uously
    -0.64
     Macro
    -0.64
     Rahman
    -0.64
     Contemporary
    -0.62
     deviation
    -0.61
    ouf
    -0.58
     Californ
    -0.57
     Bauer
    -0.57
     Brett
    -0.57
    POSITIVE LOGITS
    abouts
    0.99
     sidx
    0.91
    tical
    0.84
    through
    0.84
    anship
    0.82
    retty
    0.77
    ithub
    0.75
    ineries
    0.75
     undet
    0.74
    =-=-=-=-
    0.74
    Act Density 0.014%

    No Known Activations