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

    Neuronpedia

    INDEX
    Explanations

    Punctuation marks and abbreviated terms related to people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities denoted by initials or acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jah
    -0.65
     Vulkan
    -0.61
    imore
    -0.57
    bett
    -0.57
     voices
    -0.55
    azeera
    -0.55
     Mara
    -0.55
     capsule
    -0.54
    ibrary
    -0.54
     Zed
    -0.53
    POSITIVE LOGITS
     Lovecraft
    0.88
    ongyang
    0.85
    ERSON
    0.80
    ivot
    0.80
    sylvania
    0.73
    ople
    0.70
    EED
    0.69
    erto
    0.68
    ĵĺ
    0.68
    essor
    0.68
    Act Density 0.045%

    No Known Activations