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

    Neuronpedia

    INDEX
    Explanations

    words or names ending in 's'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "s."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.74
     fuss
    -0.71
    LEASE
    -0.70
    SIGN
    -0.70
    EStream
    -0.67
    âĢ¢âĢ¢
    -0.66
    £ı
    -0.66
    uliffe
    -0.65
     duplicate
    -0.64
    FINE
    -0.63
    POSITIVE LOGITS
    ources
    1.29
    ourced
    1.13
    ourcing
    1.10
    ouls
    1.08
    kaya
    1.08
    linger
    1.06
    essions
    1.06
    addle
    1.04
    omew
    1.03
    atisf
    1.00
    Act Density 0.419%

    No Known Activations