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

    Neuronpedia

    INDEX
    Explanations

    JavaScript code snippets

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and separators in code or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ghan
    -0.69
    .–
    -0.62
    iola
    -0.61
    !'"
    -0.60
    olo
    -0.60
    hunt
    -0.59
    âĢIJ
    -0.58
    itational
    -0.58
     passionately
    -0.58
    going
    -0.57
    POSITIVE LOGITS
    false
    0.92
     })
    0.91
     ],
    0.90
    true
    0.90
    ...)
    0.88
     },
    0.88
    ioch
    0.88
     "\
    0.86
     "$:/
    0.86
    NULL
    0.84
    Act Density 0.064%

    No Known Activations