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

    Neuronpedia

    INDEX
    Explanations

    phrases related to crossing physical or metaphorical boundaries

    oai_token-act-pair · gpt-3.5-turbo

    references to boundaries and limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PDATE
    -0.84
    ufact
    -0.73
    LESS
    -0.71
    trak
    -0.69
     srfAttach
    -0.64
    Lago
    -0.62
     piv
    -0.61
     tuning
    -0.61
     shaping
    -0.61
    essen
    -0.61
    POSITIVE LOGITS
    border
    0.73
     boundaries
    0.72
     continents
    0.72
    atars
    0.71
     threshold
    0.70
     borders
    0.69
    cross
    0.67
    abad
    0.67
     paths
    0.67
    monary
    0.66
    Act Density 0.060%

    No Known Activations