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

    Neuronpedia

    INDEX
    Explanations

    mentions of U.S. states

    oai_token-act-pair · gpt-3.5-turbo

    mentions of U.S. states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Rocket
    -0.74
     Pastebin
    -0.72
    sett
    -0.69
     Notting
    -0.66
    ADS
    -0.64
    ortun
    -0.63
     Maw
    -0.63
     Lect
    -0.59
    rious
    -0.59
     Voy
    -0.59
    POSITIVE LOGITS
    manship
    1.07
     legislatures
    0.98
    rooms
    0.86
    chool
    0.86
     legalizing
    0.84
    ide
    0.84
    boro
    0.83
    men
    0.80
     legalize
    0.79
    wide
    0.79
    Act Density 0.026%

    No Known Activations