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

    Neuronpedia

    INDEX
    Explanations

    references to Roman numerals and similarly formatted citations or enumerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewise
    -0.19
    zas
    -0.16
    leased
    -0.15
    /Dk
    -0.15
    GMEM
    -0.14
    egin
    -0.14
    /inet
    -0.14
    otte
    -0.13
    alat
    -0.13
    assen
    -0.13
    POSITIVE LOGITS
    III
    0.44
     III
    0.41
    II
    0.36
     II
    0.35
     IV
    0.32
     iii
    0.32
    iii
    0.31
     VIII
    0.31
     VII
    0.31
    IV
    0.29
    Act Density 0.043%

    No Known Activations