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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     -*-č↵
    -0.20
    ovi
    -0.17
    anza
    -0.15
    Ó
    -0.15
     èŃ
    -0.14
     Ging
    -0.14
    ovice
    -0.14
    mailer
    -0.14
    enthal
    -0.13
    /docs
    -0.13
    POSITIVE LOGITS
     deeds
    0.15
    spinner
    0.15
    blas
    0.15
     Yard
    0.14
     tavs
    0.14
    PIP
    0.14
    Ctl
    0.14
    oder
    0.14
    ATAL
    0.14
    зÑĮ
    0.14
    Act Density 0.005%

    No Known Activations