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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating official actions or status changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seper
    -0.16
    ansa
    -0.15
    jal
    -0.15
     Petr
    -0.15
    elihood
    -0.15
     promin
    -0.14
    anger
    -0.14
    prung
    -0.14
    rame
    -0.14
    ande
    -0.13
    POSITIVE LOGITS
     thái
    0.15
     pari
    0.14
    .mu
    0.14
    XYZ
    0.14
    wise
    0.14
    _linked
    0.14
    BERS
    0.14
    amız
    0.14
    relu
    0.13
    _FOLDER
    0.13
    Act Density 0.000%

    No Known Activations