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

    Neuronpedia

    INDEX
    Explanations

    the word "Conn" with different variations in the surrounding text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Conn" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bulgar
    -0.73
    anwhile
    -0.69
     behav
    -0.66
     pseud
    -0.66
     civ
    -0.65
    andr
    -0.65
    leased
    -0.65
     materials
    -0.64
    uyomi
    -0.64
    DragonMagazine
    -0.62
    POSITIVE LOGITS
     Conn
    1.13
    Conn
    1.10
    acht
    1.00
    olly
    0.98
     Smy
    0.89
    elly
    0.89
    aught
    0.85
    isco
    0.81
    agher
    0.80
    icol
    0.79
    Act Density 0.009%

    No Known Activations