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

    Neuronpedia

    INDEX
    Explanations

    references to modes of transportation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "by" followed by a numerical value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SPONSORED
    -0.73
    actly
    -0.66
    ilib
    -0.65
    inations
    -0.65
    llor
    -0.65
    TB
    -0.65
    BSD
    -0.64
    itives
    -0.64
    igi
    -0.63
    istant
    -0.62
    POSITIVE LOGITS
     virtue
    1.26
     mistake
    1.07
    catch
    1.05
    akuya
    1.02
    products
    1.01
    gone
    0.98
     accident
    0.97
     default
    0.94
    pass
    0.94
     fiat
    0.91
    Act Density 0.141%

    No Known Activations