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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating limitations or constraints

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a limitation or restriction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ult
    -0.69
    auga
    -0.67
    ameron
    -0.67
    robat
    -0.63
    ashington
    -0.63
    axis
    -0.63
    yssey
    -0.63
    umping
    -0.61
    itch
    -0.61
    loo
    -0.60
    POSITIVE LOGITS
     spor
    0.91
     marginally
    0.76
     ONE
    0.73
     insofar
    0.70
     superficial
    0.67
     finite
    0.67
     sporadic
    0.66
     fraction
    0.66
    iffe
    0.66
    ifiable
    0.66
    Act Density 0.400%

    No Known Activations