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

    Neuronpedia

    INDEX
    Explanations

    references to scientific concepts or fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    дина
    -0.16
    odyn
    -0.16
    бол
    -0.15
    ewitness
    -0.15
    inalg
    -0.15
    entiful
    -0.14
    -ce
    -0.14
    bomb
    -0.14
    mando
    -0.14
    RLF
    -0.14
    POSITIVE LOGITS
     Zuk
    0.21
    uf
    0.17
    веÑī
    0.17
    esh
    0.16
     lifts
    0.14
     Lud
    0.14
    Z
    0.14
     Hasan
    0.14
    _EXTENSIONS
    0.14
     Mush
    0.14
    Act Density 0.022%

    No Known Activations