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

    Neuronpedia

    INDEX
    Explanations

    adjectives ending in 'y' and proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'y' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ************
    -0.59
     minds
    -0.58
     Editors
    -0.55
    İĭ
    -0.55
    asket
    -0.54
     thirds
    -0.53
     Frankfurt
    -0.52
     fracturing
    -0.52
     ÙĪ
    -0.51
     MIA
    -0.51
    POSITIVE LOGITS
    y
    3.93
    yy
    2.01
    yk
    1.92
    yah
    1.90
    yi
    1.86
    yt
    1.85
    yg
    1.84
    yz
    1.76
    Y
    1.64
    yan
    1.62
    Act Density 0.049%

    No Known Activations