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

    Neuronpedia

    INDEX
    Explanations

    comparisons of varying degrees or amounts

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers that amplify comparisons or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.65
    clud
    -0.62
     psyche
    -0.62
     blocker
    -0.61
    itute
    -0.61
    tions
    -0.59
     topic
    -0.59
     lobby
    -0.59
     Library
    -0.58
    venant
    -0.58
    POSITIVE LOGITS
     fewer
    0.95
     ample
    0.86
    limited
    0.83
     varying
    0.83
    adequ
    0.82
     considerable
    0.82
     minimal
    0.81
     adequate
    0.81
     substantial
    0.81
     extensive
    0.80
    Act Density 0.265%

    No Known Activations