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

    Neuronpedia

    INDEX
    Explanations

    proper names, likely related to technology or gaming

    oai_token-act-pair · gpt-3.5-turbo

    mentions of people or notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .")
    -0.77
    ]."
    -0.71
     attRot
    -0.69
    .).
    -0.68
    sic
    -0.68
    )).
    -0.67
    cms
    -0.66
    '."
    -0.66
    >.
    -0.65
    $.
    -0.62
    POSITIVE LOGITS
     FG
    0.59
     Avalon
    0.57
     renamed
    0.54
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.54
    ometown
    0.53
     Located
    0.53
     Originally
    0.52
     hybrids
    0.52
     Buenos
    0.51
    amia
    0.50
    Act Density 1.153%

    No Known Activations