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

    Neuronpedia

    INDEX
    Explanations

    numbers and terms related to technology and programming languages

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geography and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pseudonym
    -0.62
     Weeks
    -0.54
     hay
    -0.51
     WARN
    -0.50
     Stard
    -0.50
     Rasmussen
    -0.49
     catalogue
    -0.48
     guarantee
    -0.48
     dedication
    -0.47
     guarantees
    -0.46
    POSITIVE LOGITS
    itto
    0.79
    /$
    0.62
    cellaneous
    0.62
    swick
    0.60
    mbuds
    0.59
     meanwhile
    0.59
     (-
    0.55
    emetery
    0.55
    Õ
    0.55
    Also
    0.55
    Act Density 1.128%

    No Known Activations