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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing extremes or superlatives

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing extremes or superlatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iture
    -0.83
    kamp
    -0.73
    matter
    -0.70
    culosis
    -0.70
    tera
    -0.69
    iage
    -0.69
    unity
    -0.67
    arity
    -0.67
    hyde
    -0.66
    gow
    -0.66
    POSITIVE LOGITS
     sorts
    0.85
     earners
    0.79
     course
    0.71
     ones
    0.70
     disappoint
    0.70
     incarn
    0.69
     highs
    0.68
     kin
    0.68
     classes
    0.66
     ours
    0.65
    Act Density 0.064%

    No Known Activations