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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a call to action, particularly links for more information or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apult
    -0.17
    enville
    -0.15
    iffin
    -0.15
    ιά
    -0.14
    uitka
    -0.14
    便
    -0.14
    ÑĮко
    -0.14
    mentation
    -0.14
    celik
    -0.14
     suf
    -0.13
    POSITIVE LOGITS
     fore
    0.17
    /tasks
    0.14
    GRADE
    0.14
    ford
    0.14
    fore
    0.14
    å¼
    0.14
    arah
    0.14
    稿
    0.14
    udd
    0.13
    affen
    0.13
    Act Density 0.009%

    No Known Activations