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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest causation or relationships in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Someone
    -0.73
    You
    -0.72
    Someone
    -0.72
    you
    -0.70
     someone
    -0.69
     you
    -0.67
     Everyone
    -0.67
     YOU
    -0.65
     Somebody
    -0.63
    Everyone
    -0.63
    POSITIVE LOGITS
    stantial
    0.78
     such
    0.72
    StructEnd
    0.70
    considerable
    0.68
    ")"
    0.67
     recent
    0.67
     differences
    0.66
     significant
    0.66
     substantial
    0.63
    ConfigureAwait
    0.63
    Act Density 1.317%

    No Known Activations