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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms or code snippets

    oai_token-act-pair · gpt-3.5-turbo

    programming elements and code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .''
    -0.65
    .).
    -0.62
    .}
    -0.61
     skelet
    -0.60
    .</
    -0.59
    .]
    -0.59
     sugg
    -0.58
     outwe
    -0.57
     constellation
    -0.57
     fundament
    -0.56
    POSITIVE LOGITS
    roma
    0.86
    %:
    0.82
     Heist
    0.76
     Printed
    0.74
     Miscellaneous
    0.68
     Theft
    0.68
    intosh
    0.67
    ãĥį
    0.65
     Detected
    0.64
     Releases
    0.64
    Act Density 0.286%

    No Known Activations