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

    Neuronpedia

    INDEX
    Explanations

    countries and cities

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conservancy
    -0.76
    ixel
    -0.74
    ibble
    -0.72
    WARE
    -0.69
    ":"/
    -0.68
    BIP
    -0.65
    raught
    -0.63
    Leaks
    -0.63
    tera
    -0.62
    âĸĵ
    -0.61
    POSITIVE LOGITS
     etc
    1.07
    etc
    1.06
     assorted
    0.99
     others
    0.86
    rogens
    0.84
     possibly
    0.77
     other
    0.75
     ect
    0.71
     optionally
    0.68
    rogen
    0.67
    Act Density 0.217%

    No Known Activations