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

    Neuronpedia

    INDEX
    Explanations

    code snippets and string formatting patterns

    oai_token-act-pair · gpt-3.5-turbo

    elements related to programming code and data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ividual
    -0.92
    ammy
    -0.89
    ndra
    -0.79
    ulla
    -0.75
     synerg
    -0.71
    osures
    -0.71
    lees
    -0.70
    rollers
    -0.69
    gdala
    -0.69
    agonist
    -0.68
    POSITIVE LOGITS
    UTF
    1.51
     UTF
    1.35
    utf
    1.26
     Unicode
    1.18
    ISO
    1.16
     ASCII
    1.06
    ASC
    0.93
     encoding
    0.93
     chars
    0.90
    çīĪ
    0.88
    Act Density 0.103%

    No Known Activations