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

    Neuronpedia

    INDEX
    Explanations

    adjectives or descriptors related to qualities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    al
    -0.76
     is
    -0.74
     can
    -0.70
    -
    -0.69
     only
    -0.66
     was
    -0.65
     uğ
    -0.64
    or
    -0.64
     about
    -0.63
    n
    -0.63
    POSITIVE LOGITS
     Italijanski
    1.32
     estekak
    1.23
    EDEFAULT
    1.16
     Мексичка
    1.14
     '\\;'
    1.14
     дописавши
    1.13
    )";
    1.10
    }")
    1.08
    RenderAtEndOf
    1.08
     Himo
    1.08
    Act Density 0.022%

    No Known Activations