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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "My" followed by a proper noun or specific term

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "my."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itect
    -0.80
    OPLE
    -0.77
    inelli
    -0.72
    igham
    -0.72
    DERR
    -0.69
     Uriel
    -0.69
    ieri
    -0.67
    itud
    -0.67
    INO
    -0.67
    س
    -0.66
    POSITIVE LOGITS
    stery
    1.43
    anmar
    1.30
    riad
    1.18
    stic
    1.14
    ths
    1.11
    self
    1.10
    chal
    1.00
    ocard
    0.98
    opia
    0.96
    gdala
    0.94
    Act Density 0.055%

    No Known Activations