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

    Neuronpedia

    INDEX
    Explanations

    technical terms and references related to a specific programming language or project

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ential
    -0.68
     Combine
    -0.66
    ggies
    -0.65
    ãĤī
    -0.65
    CAST
    -0.63
    YC
    -0.62
     LCS
    -0.61
    xit
    -0.61
     Measures
    -0.59
     Primordial
    -0.59
    POSITIVE LOGITS
    rors
    1.31
    rored
    1.29
    acles
    1.29
    acle
    1.16
    abella
    1.03
    ror
    1.01
    abilia
    0.97
    ial
    0.91
    iam
    0.89
    abel
    0.86
    Act Density 0.067%

    No Known Activations