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

    Neuronpedia

    INDEX
    Explanations

    references to political assemblies

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative bodies or assemblies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ¦
    -0.76
    zsche
    -0.74
    onyms
    -0.73
    ãĤ¨ãĥ«
    -0.68
    ties
    -0.67
    PLIED
    -0.66
    wolves
    -0.63
    utical
    -0.63
    kus
    -0.62
    ograp
    -0.61
    POSITIVE LOGITS
     Speaker
    1.04
     Assembly
    0.98
    Assembly
    0.97
    member
    0.92
    woman
    0.89
     assembly
    0.85
     speaker
    0.85
    sembly
    0.84
    undo
    0.78
     chamber
    0.77
    Act Density 0.007%

    No Known Activations