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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating impossibility or prohibition

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express inability or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancer
    -0.65
    casting
    -0.65
     Generation
    -0.65
     Five
    -0.63
    liter
    -0.62
    bats
    -0.62
    ieu
    -0.61
    offs
    -0.60
     Loaded
    -0.60
    pocket
    -0.59
    POSITIVE LOGITS
    ĸļ
    1.11
     reproduce
    0.89
     necessarily
    0.88
     afford
    0.87
    adian
    0.86
    berra
    0.85
    't
    0.85
     exceed
    0.83
     attest
    0.80
     Canaver
    0.79
    Act Density 0.020%

    No Known Activations