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

    Neuronpedia

    INDEX
    Explanations

    punctuation and author identifiers in literary reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jab
    -0.17
    å®Ļ
    -0.15
    607
    -0.15
    887
    -0.15
     Finals
    -0.14
    aiser
    -0.14
    ayne
    -0.14
    ait
    -0.14
    _TEMP
    -0.14
    678
    -0.14
    POSITIVE LOGITS
    raquo
    0.17
    OTAL
    0.14
     Hüs
    0.14
    _hooks
    0.14
    ahir
    0.14
    EMPL
    0.13
    UNC
    0.13
    ¦
    0.13
    BIND
    0.13
    eless
    0.13
    Act Density 0.014%

    No Known Activations