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

    Neuronpedia

    INDEX
    Explanations

    precise measurements or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to precision and accuracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orship
    -0.63
    news
    -0.62
    bean
    -0.61
    agues
    -0.60
    warts
    -0.60
    walk
    -0.60
     Semin
    -0.59
    ublic
    -0.58
    andal
    -0.58
    osphere
    -0.58
    POSITIVE LOGITS
     precise
    3.41
     exact
    2.29
     accurate
    1.73
     precision
    1.63
     precisely
    1.41
     specific
    1.40
     meticulous
    1.39
     careful
    1.36
    cise
    1.36
     detailed
    1.30
    Act Density 0.007%

    No Known Activations