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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting in software documentation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     незавершена
    -0.91
     الحره
    -0.90
    ftagPool
    -0.90
     يتيمه
    -0.89
     Roskov
    -0.85
     beginnetje
    -0.85
     kasarigan
    -0.84
     Walkover
    -0.82
     EnglishChoose
    -0.81
    ...')
    -0.79
    POSITIVE LOGITS
    ‘
    0.47
     hi
    0.47
    EREF
    0.46
    佐
    0.46
    sohn
    0.46
     podido
    0.45
     نم
    0.45
    ’
    0.45
    hoop
    0.44
     potuto
    0.43
    Act Density 0.007%

    No Known Activations