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

    Neuronpedia

    INDEX
    Explanations

    quotes and sayings within the text

    oai_token-act-pair · gpt-3.5-turbo

    well-known sayings or quotes, particularly those related to common beliefs or wisdom

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essions
    -0.70
    jri
    -0.70
    pson
    -0.70
     contrace
    -0.70
    etting
    -0.67
    ensing
    -0.67
    gur
    -0.66
    elsen
    -0.66
    adesh
    -0.65
    obin
    -0.64
    POSITIVE LOGITS
     Unle
    0.75
     \"
    0.73
     proverb
    0.72
     aph
    0.71
    okingly
    0.70
     `
    0.70
     famously
    0.70
     mant
    0.70
     Interpret
    0.69
     phrase
    0.69
    Act Density 0.253%

    No Known Activations