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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that contain clear separators or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     positives
    -0.69
     crank
    -0.68
    LECT
    -0.67
     paranormal
    -0.66
     sque
    -0.65
     CEOs
    -0.63
     Logged
    -0.62
     envy
    -0.62
     multit
    -0.62
     spirited
    -0.62
    POSITIVE LOGITS
    opolis
    1.07
    ulia
    1.06
    apan
    1.01
    onia
    0.98
    alla
    0.96
    abad
    0.96
    burgh
    0.95
    inav
    0.95
    agar
    0.94
    ussia
    0.93
    Act Density 0.264%

    No Known Activations