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

    Neuronpedia

    INDEX
    Explanations

    instances of numeric values, potentially related to data or configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atham
    -0.17
    apped
    -0.16
    راÙĨ
    -0.15
    vala
    -0.14
    605
    -0.14
    ngo
    -0.14
    pedo
    -0.14
    acks
    -0.13
     Lever
    -0.13
    Assertions
    -0.13
    POSITIVE LOGITS
     fisse
    0.17
    menin
    0.16
    mani
    0.15
    zl
    0.14
    ily
    0.14
    rek
    0.14
    kers
    0.14
    lash
    0.14
    jab
    0.14
    uzzi
    0.14
    Act Density 0.013%

    No Known Activations