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

    Neuronpedia

    INDEX
    Explanations

    references to typing and written communication processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anger
    -0.17
     ex
    -0.17
     Dean
    -0.15
     Scho
    -0.15
    åĬ
    -0.15
     your
    -0.14
     Gall
    -0.14
     Sc
    -0.14
    ment
    -0.14
    kind
    -0.14
    POSITIVE LOGITS
    addock
    0.17
    _compat
    0.16
     seiz
    0.16
    RowAt
    0.15
    mailer
    0.15
    /email
    0.14
    ávÄĽ
    0.14
    æĭ©
    0.14
    OutputStream
    0.14
     ì¦
    0.14
    Act Density 0.027%

    No Known Activations