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

    Neuronpedia

    INDEX
    Explanations

    texts discussing fundamental concepts or ideas

    oai_token-act-pair · gpt-3.5-turbo

    references to fundamental concepts or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nery
    -0.75
    quer
    -0.74
     Volunteers
    -0.73
    peak
    -0.72
    oping
    -0.72
    kers
    -0.70
    pless
    -0.70
    haw
    -0.70
    crow
    -0.69
    annis
    -0.69
    POSITIVE LOGITS
     tenets
    0.96
     principles
    0.91
    ists
    0.83
     importance
    0.83
     essence
    0.81
    izes
    0.81
     elements
    0.81
     fundamental
    0.80
     principle
    0.80
     flaw
    0.80
    Act Density 0.014%

    No Known Activations