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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a comparison of different qualities or attributes

    oai_token-act-pair · gpt-3.5-turbo

    descriptive phrases that indicate the quality or condition of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Footnote
    -0.64
    achment
    -0.60
    ench
    -0.55
     âĻ
    -0.54
    ppa
    -0.54
     Goddess
    -0.54
     refresh
    -0.53
    oire
    -0.52
     pump
    -0.52
     Ago
    -0.51
    POSITIVE LOGITS
     termed
    1.14
     arguably
    1.05
     essentially
    1.01
     billed
    0.99
     ordinarily
    0.97
     rightfully
    0.93
     otherwise
    0.90
     aptly
    0.90
     euphem
    0.88
     undoubtedly
    0.88
    Act Density 0.058%

    No Known Activations