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

    Neuronpedia

    INDEX
    Explanations

    references to cookies and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouro
    -0.20
    á»ĵng
    -0.15
     Kle
    -0.15
    ingers
    -0.15
    ste
    -0.14
     civilian
    -0.14
    ousse
    -0.14
     cos
    -0.14
    shal
    -0.14
    eward
    -0.14
    POSITIVE LOGITS
     Jarvis
    0.17
    ald
    0.16
    antha
    0.15
    igsaw
    0.14
    />.
    0.14
     Hein
    0.14
    arsity
    0.14
    ERNEL
    0.14
    gens
    0.13
    _FATAL
    0.13
    Act Density 0.002%

    No Known Activations