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

    Neuronpedia

    INDEX
    Explanations

    California-related terms, especially locations within California

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     contraceptives
    -0.64
    theless
    -0.62
    xual
    -0.62
     Crimean
    -0.62
     ejac
    -0.61
     caution
    -0.60
    TPPStreamerBot
    -0.60
     livest
    -0.59
    balance
    -0.59
     handshake
    -0.59
    POSITIVE LOGITS
    sis
    1.01
    onia
    0.93
    ubs
    0.81
    arro
    0.81
    rez
    0.80
    ares
    0.80
    inct
    0.79
    eno
    0.79
    ubes
    0.79
    azz
    0.78
    Act Density 6.709%

    No Known Activations