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

    Neuronpedia

    INDEX
    Explanations

    mentions of the programming language "Lisp"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific programming language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Valent
    -0.74
    strate
    -0.72
     bear
    -0.70
    DER
    -0.67
    âĸ¬âĸ¬
    -0.66
    çĦ
    -0.64
    stri
    -0.64
     Haj
    -0.63
     Halls
    -0.62
    ãĥ¼ãĥ«
    -0.61
    POSITIVE LOGITS
    ensable
    1.15
    olicy
    1.10
    olitics
    1.08
    herical
    1.06
    heric
    0.99
    irit
    0.94
    aque
    0.94
    ython
    0.93
    unct
    0.89
    acet
    0.88
    Act Density 0.012%

    No Known Activations