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

    Neuronpedia

    INDEX
    Explanations

    adverbs that describe the degree or intensity of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sharply."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rity
    -0.80
    itu
    -0.79
    gres
    -0.73
    ioch
    -0.72
    sites
    -0.71
    orno
    -0.70
    omnia
    -0.67
    nan
    -0.67
     Territories
    -0.67
    tein
    -0.67
    POSITIVE LOGITS
     tuned
    0.85
     diver
    0.82
     sharply
    0.80
     deline
    0.76
     downwards
    0.73
     downward
    0.71
     distingu
    0.70
     contrad
    0.70
     divergence
    0.69
     distinguish
    0.69
    Act Density 0.007%

    No Known Activations