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

    geographical locations or state names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.73
     mast
    -0.59
    adobe
    -0.58
     Crimean
    -0.56
     Clicker
    -0.55
     fore
    -0.55
     macro
    -0.54
     blink
    -0.53
     Shades
    -0.52
     Grail
    -0.52
    POSITIVE LOGITS
    .,
    1.93
    .;
    1.62
    .:
    1.51
    .,"
    1.41
    .-
    1.40
    .?
    1.39
    .—
    1.38
    ./
    1.38
    .--
    1.33
    .),
    1.29
    Act Density 0.056%

    No Known Activations