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

    Neuronpedia

    INDEX
    Explanations

    references to software libraries (specifically "lib")

    oai_token-act-pair · gpt-3.5-turbo

    mentions of libraries, particularly in a programming or software context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Oaks
    -0.73
     boarding
    -0.69
    OPLE
    -0.68
     Forever
    -0.64
     silence
    -0.63
     Huh
    -0.62
    hower
    -0.61
     tallest
    -0.61
     lodge
    -0.60
     Empires
    -0.59
    POSITIVE LOGITS
    virt
    1.00
    png
    0.83
    tier
    0.82
    glers
    0.82
     lib
    0.82
    enh
    0.80
    tool
    0.79
    phen
    0.79
    hered
    0.79
    ido
    0.78
    Act Density 0.009%

    No Known Activations