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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms related to various fields of study like computer science, engineering, mathematics, and medicine

    oai_token-act-pair · gpt-3.5-turbo

    references to concepts related to time and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    $.
    -0.71
    }.
    -0.65
    !.
    -0.64
    `.
    -0.62
    .<
    -0.60
    chwitz
    -0.59
     elsewhere
    -0.59
    .</
    -0.59
    utics
    -0.58
    +.
    -0.58
    POSITIVE LOGITS
    iest
    0.76
     analogy
    0.76
     portion
    0.70
     dilemma
    0.69
     hypothesis
    0.69
    osphere
    0.68
     aspect
    0.68
    ariat
    0.62
     gap
    0.62
    hest
    0.61
    Act Density 1.180%

    No Known Activations