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

    Neuronpedia

    INDEX
    Explanations

    text related to programming strings or data types

    oai_token-act-pair · gpt-3.5-turbo

    terms related to strings and string data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -0.84
    zona
    -0.84
    laus
    -0.82
    forces
    -0.77
    kens
    -0.76
    espie
    -0.75
    mares
    -0.74
    undai
    -0.74
    addons
    -0.73
    egal
    -0.72
    POSITIVE LOGITS
     literal
    1.06
     liter
    0.97
    acters
    0.87
    ified
    0.86
     representation
    0.80
     representations
    0.78
    ify
    0.77
    UTF
    0.75
    ifying
    0.75
     delim
    0.72
    Act Density 0.019%

    No Known Activations