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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names ending with 'ille'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific location or place name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaries
    -0.98
    etheless
    -0.88
    -+-+
    -0.84
    iary
    -0.83
    ortium
    -0.82
    reme
    -0.81
    uyomi
    -0.78
    ulously
    -0.77
    icum
    -0.74
    icist
    -0.74
    POSITIVE LOGITS
    tto
    1.21
    hammer
    0.93
    lla
    0.89
    tt
    0.88
    sburg
    0.87
    ville
    0.87
    ttes
    0.83
    isure
    0.80
    brand
    0.79
     Hebdo
    0.79
    Act Density 0.019%

    No Known Activations