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

    Neuronpedia

    INDEX
    Explanations

    words with the suffix 'ful', indicating positivity or abundance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etical
    -0.17
    alled
    -0.15
    ical
    -0.15
    arah
    -0.15
    IDEO
    -0.14
    ARY
    -0.14
    egas
    -0.14
     chứng
    -0.14
    zelf
    -0.14
    et
    -0.13
    POSITIVE LOGITS
    ness
    0.28
    NESS
    0.25
    lest
    0.25
    mente
    0.15
    s
    0.15
    iagnostics
    0.15
    nes
    0.15
    .Factory
    0.14
    -looking
    0.14
    trait
    0.14
    Act Density 0.042%

    No Known Activations