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

    Neuronpedia

    INDEX
    Explanations

    phrases related to restrictions and limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fried
    -0.15
     либо
    -0.15
    etus
    -0.15
    ddl
    -0.14
    .va
    -0.14
    ippers
    -0.14
    екÑĥ
    -0.14
    ubber
    -0.13
    ubbo
    -0.13
    ¤íĶĦ
    -0.13
    POSITIVE LOGITS
     beyond
    0.37
     besides
    0.36
     Beyond
    0.31
     além
    0.28
    Beyond
    0.28
    eyond
    0.28
     oltre
    0.28
    éĻ¤äºĨ
    0.24
     Besides
    0.23
     apart
    0.23
    Act Density 0.211%

    No Known Activations