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

    Neuronpedia

    INDEX
    Explanations

    instances where requests for comments are mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to comments from entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    course
    -0.68
    ccording
    -0.68
    hab
    -0.67
     Sinai
    -0.66
    tail
    -0.66
    locked
    -0.65
    corn
    -0.63
     habitable
    -0.63
    gran
    -0.62
    YP
    -0.62
    POSITIVE LOGITS
    ariat
    1.04
    ysis
    0.92
    ature
    0.85
    atures
    0.82
    ispers
    0.81
     comment
    0.77
    natureconservancy
    0.75
    aires
    0.74
     ado
    0.71
    ivity
    0.71
    Act Density 0.028%

    No Known Activations