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

    Neuronpedia

    INDEX
    Explanations

    instances of proper names and titles, particularly relating to authors and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Binding
    -0.15
    grave
    -0.15
    ooting
    -0.15
    ertz
    -0.15
    ieri
    -0.14
    egg
    -0.14
    wner
    -0.14
    uche
    -0.14
    екÑĤ
    -0.13
    uve
    -0.13
    POSITIVE LOGITS
    ãģıãģł
    0.15
    æĹģ
    0.15
    atform
    0.15
    aight
    0.14
    verted
    0.14
    æľĭ
    0.14
    aires
    0.14
     EntityState
    0.13
    avar
    0.13
    ÐIJÑĢÑħÑĸв
    0.13
    Act Density 0.043%

    No Known Activations