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

    Neuronpedia

    INDEX
    Explanations

    phrases related to voting

    oai_token-act-pair · gpt-3.5-turbo

    the concept of plebiscites or public votes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Emerging
    -0.74
    master
    -0.72
    ANA
    -0.71
    uador
    -0.69
    Root
    -0.68
    DERR
    -0.67
     Accounting
    -0.66
    Dash
    -0.66
     Roots
    -0.65
     Fired
    -0.65
    POSITIVE LOGITS
     ple
    1.55
    ases
    0.91
    ptin
    0.87
    asure
    0.85
    ple
    0.83
    ggle
    0.83
     Ple
    0.82
     plead
    0.82
    ply
    0.82
     pled
    0.81
    Act Density 0.005%

    No Known Activations