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

    Neuronpedia

    INDEX
    Explanations

    adverbs that emphasize the degree or intensity of an action or attribute

    oai_token-act-pair · gpt-3.5-turbo

    strong adjectives indicating significant changes or increases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gres
    -0.73
    ividual
    -0.71
    acity
    -0.69
    rity
    -0.69
    ourke
    -0.68
    pty
    -0.68
    guyen
    -0.67
    ioch
    -0.66
     Farmers
    -0.66
    busters
    -0.66
    POSITIVE LOGITS
     diver
    0.83
     tuned
    0.82
     sharply
    0.78
     downwards
    0.77
    cut
    0.77
     downward
    0.76
     distingu
    0.73
     curtail
    0.72
     distinguish
    0.71
     discontin
    0.70
    Act Density 0.016%

    No Known Activations