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

    Neuronpedia

    INDEX
    Explanations

    words starting with lowercase letters and have more than three characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "words"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olyn
    -0.72
    ño
    -0.71
    DERR
    -0.70
    ©¶æ¥µ
    -0.69
    psey
    -0.67
    etheus
    -0.66
    ameron
    -0.66
    ntil
    -0.65
    roxy
    -0.64
    yss
    -0.64
    POSITIVE LOGITS
    mith
    1.33
     words
    1.15
    terday
    1.05
    words
    1.03
    sworth
    0.98
     aloud
    0.88
     Words
    0.85
     uttered
    0.83
    Words
    0.82
    speak
    0.79
    Act Density 0.017%

    No Known Activations