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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     –↵↵
    -0.16
    ![↵
    -0.15
    ÃľR
    -0.15
     -↵
    -0.15
     ...↵↵
    -0.14
    èŃľ
    -0.14
    'y
    -0.14
    .gb
    -0.13
     –↵
    -0.13
    ä½
    -0.13
    POSITIVE LOGITS
    :
    0.20
    aldi
    0.18
     learner
    0.17
     I
    0.17
    5
    0.17
    4
    0.16
    310
    0.16
     esl
    0.16
     learners
    0.16
     tion
    0.16
    Act Density 0.000%

    No Known Activations