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

    Neuronpedia

    INDEX
    Explanations

    references to pronouns and related structures in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XmlAccessType
    -0.63
    ValueStyle
    -0.54
    حياته
    -0.50
    ]--;
    -0.49
    awtextra
    -0.49
    DllImport
    -0.49
    WindowListener
    -0.48
    mbros
    -0.48
    mony
    -0.46
    ÑOS
    -0.46
    POSITIVE LOGITS
    LICENSE
    0.55
     esso
    0.55
    ://$
    0.55
    emails
    0.53
     judiciaire
    0.52
    +#+#
    0.52
     Numerade
    0.51
    ťaž
    0.49
     Weltkrieg
    0.49
    antaranya
    0.48
    Act Density 0.172%

    No Known Activations