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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing negative aspects or disadvantages

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the advantages and disadvantages of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SpaceEngineers
    -0.71
    EVA
    -0.68
    leasing
    -0.66
    asus
    -0.65
     frenzy
    -0.65
    ongyang
    -0.65
    uton
    -0.63
    flush
    -0.60
    caster
    -0.59
    rador
    -0.59
    POSITIVE LOGITS
     inherent
    1.07
    ayers
    1.00
    omen
    0.99
    hooting
    0.99
     outweigh
    0.99
     outwe
    0.98
    ities
    0.88
     abound
    0.88
    cale
    0.88
     pitfalls
    0.87
    Act Density 0.231%

    No Known Activations