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

    Neuronpedia

    INDEX
    Explanations

    adjectives and phrases related to characteristics of varying degrees

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe characteristics or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    staking
    -0.73
    idable
    -0.65
    ModLoader
    -0.65
     Atlantis
    -0.64
    theless
    -0.64
     reper
    -0.59
     Mills
    -0.59
     Heights
    -0.58
     Curious
    -0.58
     Palest
    -0.56
    POSITIVE LOGITS
    ities
    0.82
    tions
    0.67
    isons
    0.64
    ãĥīãĥ©
    0.64
    vice
    0.63
    fiction
    0.62
    anyl
    0.62
    ainment
    0.62
    20439
    0.61
    dies
    0.61
    Act Density 0.597%

    No Known Activations