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

    Neuronpedia

    INDEX
    Explanations

    adjectives that describe quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    adjectives that describe various qualities or conditions, particularly those that indicate size or severity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ateurs
    -0.81
    seekers
    -0.75
    avers
    -0.74
    lees
    -0.74
    bees
    -0.72
    bots
    -0.72
    asters
    -0.71
    wrong
    -0.70
    aters
    -0.70
    akings
    -0.69
    POSITIVE LOGITS
     version
    0.97
     sounding
    0.95
     scenario
    0.89
     situation
    0.88
     piece
    0.87
     thing
    0.84
     example
    0.84
     affair
    0.84
     acronym
    0.82
     model
    0.82
    Act Density 0.213%

    No Known Activations