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

    Neuronpedia

    INDEX
    Explanations

    mentions of US states

    oai_token-act-pair · gpt-3.5-turbo

    references to individual states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pastebin
    -0.70
    Rocket
    -0.69
    rious
    -0.65
     Lect
    -0.65
    sett
    -0.62
     Maw
    -0.60
     Notting
    -0.59
     Icar
    -0.59
     SPL
    -0.59
     Murd
    -0.59
    POSITIVE LOGITS
    manship
    1.10
     legislatures
    0.94
    rooms
    0.92
    men
    0.87
    chool
    0.83
    ide
    0.82
     legalizing
    0.81
    wide
    0.79
    states
    0.79
    hips
    0.78
    Act Density 0.035%

    No Known Activations