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

    Neuronpedia

    INDEX
    Explanations

    Spanish words

    oai_token-act-pair · gpt-3.5-turbo

    the repeated occurrence of certain syllables or phonetic patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atform
    -0.73
    ropolitan
    -0.62
    iscopal
    -0.58
    agged
    -0.58
     congratulated
    -0.58
     Mehran
    -0.58
     footprints
    -0.57
     razor
    -0.55
     plank
    -0.53
     wallets
    -0.53
    POSITIVE LOGITS
    lla
    1.49
    lled
    1.33
    ll
    1.32
    llo
    1.28
    hler
    1.23
    lly
    1.21
    llers
    1.20
    lling
    1.15
    hner
    1.06
    ño
    1.05
    Act Density 0.052%

    No Known Activations