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

    Neuronpedia

    INDEX
    Explanations

    locations or places where people gather

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical locations or settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -0.67
    ãĤ¢ãĥ«
    -0.66
    ivas
    -0.65
    species
    -0.65
    umn
    -0.64
    IQ
    -0.64
    CHAT
    -0.64
    è¦ļéĨĴ
    -0.62
    Weather
    -0.61
    BUR
    -0.61
    POSITIVE LOGITS
     aisle
    0.83
    atics
    0.69
     continuum
    0.68
     hierarchy
    0.68
     brawl
    0.68
    rums
    0.66
     archives
    0.65
     alone
    0.65
    tyard
    0.64
     fraternity
    0.64
    Act Density 0.364%

    No Known Activations