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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to limitations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "limited" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilon
    -0.82
    ashington
    -0.78
    tha
    -0.74
    lyn
    -0.74
    idon
    -0.68
    Gener
    -0.68
    mol
    -0.67
    Tam
    -0.66
    HEAD
    -0.65
    CENT
    -0.65
    POSITIVE LOGITS
     minded
    0.88
    inous
    0.86
     amounts
    0.84
     amount
    0.83
     exceptions
    0.82
     quantities
    0.77
     lifespan
    0.75
    sighted
    0.74
     collateral
    0.74
     liability
    0.74
    Act Density 0.035%

    No Known Activations