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

    Neuronpedia

    INDEX
    Explanations

    adjectives or terms expressing extremity or intensity

    oai_token-act-pair · gpt-3.5-turbo

    descriptors of intensity or extremity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anders
    -0.79
    ploma
    -0.70
    ADS
    -0.66
    andering
    -0.65
    APH
    -0.65
    aden
    -0.64
    annis
    -0.64
    antics
    -0.64
    conservancy
    -0.63
    adr
    -0.61
    POSITIVE LOGITS
    ly
    2.89
    LY
    1.85
    liness
    1.41
    lys
    1.37
    fully
    1.33
    lies
    1.30
    ELY
    1.27
    edly
    1.20
    liest
    1.15
    ity
    1.09
    Act Density 0.173%

    No Known Activations