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

    Neuronpedia

    INDEX
    Explanations

    numbers related to specific dates or quantitative values

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of numerical data and coding syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     academia
    -0.63
     obscurity
    -0.61
     plagiar
    -0.60
     incompetence
    -0.58
     stupidity
    -0.57
     sanity
    -0.57
     satire
    -0.57
     scams
    -0.56
     hindsight
    -0.55
     spoiler
    -0.55
    POSITIVE LOGITS
    ividually
    0.66
    .;
    0.64
    ;
    0.62
    ();
    0.61
    zona
    0.60
     (+
    0.58
    ½
    0.58
     ();
    0.58
    bery
    0.58
    engers
    0.57
    Act Density 0.928%

    No Known Activations