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

    Neuronpedia

    INDEX
    Explanations

    code snippets and programming-related words

    oai_token-act-pair · gpt-3.5-turbo

    opening parentheses in code or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢij
    -0.75
     ransom
    -0.73
    entimes
    -0.72
     handc
    -0.70
     wart
    -0.67
     predic
    -0.66
     incarn
    -0.66
    ylum
    -0.65
     storylines
    -0.65
     whis
    -0.65
    POSITIVE LOGITS
    ...)
    1.03
    ())
    0.99
    default
    0.92
    initial
    0.81
    selected
    0.81
    checked
    0.81
    username
    0.81
    partial
    0.81
    expr
    0.80
    ctx
    0.80
    Act Density 0.034%

    No Known Activations