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

    Neuronpedia

    INDEX
    Explanations

    the word "but" followed by a description or contrast

    oai_token-act-pair · gpt-3.5-turbo

    instances of contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lement
    -0.73
    ealing
    -0.66
    ammed
    -0.65
    esc
    -0.65
    ISH
    -0.63
    à¥
    -0.63
    aez
    -0.63
    legate
    -0.62
    adr
    -0.62
    IZ
    -0.62
    POSITIVE LOGITS
     none
    1.35
     nothing
    1.14
     mostly
    1.10
     generally
    1.01
     invariably
    1.00
     ultimately
    1.00
     alas
    1.00
     nowhere
    0.99
     overall
    0.99
     chiefly
    0.97
    Act Density 0.239%

    No Known Activations