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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptions or limitations

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing exceptions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hoop
    -0.67
     merry
    -0.63
    onew
    -0.63
    anners
    -0.62
     hurry
    -0.59
    ocratic
    -0.59
    ocrats
    -0.58
     passers
    -0.58
    rity
    -0.58
     glide
    -0.58
    POSITIVE LOGITS
     LIMITED
    0.93
     limited
    0.86
    excluding
    0.81
     limitation
    0.79
     excluding
    0.76
     excluded
    0.73
     excludes
    0.71
    minus
    0.71
    exclusive
    0.70
    including
    0.70
    Act Density 0.102%

    No Known Activations