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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate official statements or communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aad
    -0.17
    uyá»ģn
    -0.15
     Feder
    -0.15
    onical
    -0.14
    alus
    -0.14
     Misc
    -0.13
    andan
    -0.13
    Codec
    -0.13
     Flux
    -0.13
    ides
    -0.13
    POSITIVE LOGITS
    UTERS
    0.17
    UTE
    0.15
    첨ë¶Ģ
    0.15
     sublicense
    0.14
    æ®Ĭ
    0.14
    IFICATE
    0.14
    agrid
    0.13
    uters
    0.13
    ัศ
    0.13
    ress
    0.13
    Act Density 0.021%

    No Known Activations