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

    Neuronpedia

    INDEX
    Explanations

    proper nouns such as names and titles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "A" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     amps
    -0.64
    },{"
    -0.64
     stripes
    -0.63
     envy
    -0.63
     Jagu
    -0.61
     Saturdays
    -0.60
     Sundays
    -0.58
    Attach
    -0.58
     sorts
    -0.57
    åĤ
    -0.57
    POSITIVE LOGITS
    gency
    1.25
    chieve
    1.23
    ircraft
    1.19
    UTH
    1.17
    usterity
    1.17
    cknow
    1.16
    cknowled
    1.16
    verages
    1.11
    uckland
    1.09
     spokesperson
    1.03
    Act Density 0.092%

    No Known Activations