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

    Neuronpedia

    INDEX
    Explanations

    elements of dialogue and expression in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.59
    preferred
    -0.55
     IndexError
    -0.55
     ComVisible
    -0.54
    TagMode
    -0.53
    œurs
    -0.53
     KeyError
    -0.53
    BuilderFactory
    -0.52
    getRuntime
    -0.52
     determinado
    -0.52
    POSITIVE LOGITS
    THING
    1.04
     everything
    0.93
     things
    0.92
     thing
    0.92
    everything
    0.88
     stuff
    0.88
     THING
    0.87
    thing
    0.86
     Everything
    0.83
     Thing
    0.82
    Act Density 0.429%

    No Known Activations