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

    Neuronpedia

    INDEX
    Explanations

    references to instances of reporting or transmission of messages

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.63
    thenia
    -0.54
    arakhand
    -0.53
    坞
    -0.53
    ьаж
    -0.52
    Diweddarwch
    -0.52
    adpleegd
    -0.51
    ednesday
    -0.50
    EndInit
    -0.50
    rolid
    -0.50
    POSITIVE LOGITS
    Sent
    3.13
     Sent
    2.91
    SENT
    1.48
     SENT
    1.38
    Enviado
    1.09
     sentencing
    0.96
    sent
    0.93
     Sentence
    0.88
    Sentence
    0.86
     Sentences
    0.84
    Act Density 0.001%

    No Known Activations