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

    Neuronpedia

    INDEX
    Explanations

    names of films or movies

    oai_token-act-pair · gpt-3.5-turbo

    references to films and movies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LESS
    -0.70
    tenance
    -0.67
     subsistence
    -0.64
    pse
    -0.62
    votes
    -0.60
     ridge
    -0.59
    aye
    -0.59
     procedure
    -0.58
    asus
    -0.57
     disturbance
    -0.56
    POSITIVE LOGITS
    uggest
    1.14
    ettings
    1.03
    chool
    1.00
    paces
    1.00
    ynthesis
    1.00
    linger
    0.97
    ilver
    0.95
     starring
    0.90
    cape
    0.89
    hops
    0.89
    Act Density 0.142%

    No Known Activations