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

    Neuronpedia

    INDEX
    Explanations

    numerical indicators of data types or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.15
    aire
    -0.15
    Ñıл
    -0.14
    /or
    -0.14
    eenth
    -0.14
    STS
    -0.14
    upa
    -0.13
    SO
    -0.13
    nd
    -0.13
     addict
    -0.13
    POSITIVE LOGITS
    iversit
    0.16
    ayette
    0.15
    æŀ¶
    0.14
    jug
    0.14
    ofil
    0.14
    iture
    0.14
    emer
    0.13
    _utilities
    0.13
    aket
    0.13
    oldem
    0.13
    Act Density 0.008%

    No Known Activations