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

    Neuronpedia

    INDEX
    Explanations

    general concepts related to significant change or new ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Julian
    -0.15
    angered
    -0.15
    hazi
    -0.14
    .Undef
    -0.14
    laÄį
    -0.14
    .xz
    -0.14
     Roths
    -0.13
    adius
    -0.13
     Leslie
    -0.13
    çħĻ
    -0.13
    POSITIVE LOGITS
    arda
    0.17
     hạ
    0.15
     aim
    0.14
     LGPL
    0.14
    cepts
    0.14
    AttributeValue
    0.14
    viders
    0.13
    655
    0.13
     measured
    0.13
    lu
    0.13
    Act Density 0.669%

    No Known Activations