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

    Neuronpedia

    INDEX
    Explanations

    the overall assessment or summary of a given dataset or result

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     grammi
    -0.57
     generally
    -0.54
     académica
    -0.52
    ✨:
    -0.52
     NavController
    -0.51
    CreateMap
    -0.49
    vfs
    -0.49
     maneiras
    -0.48
     moreover
    -0.47
    FAA
    -0.47
    POSITIVE LOGITS
    Overall
    1.59
     Overall
    1.58
    Fazit
    0.89
     Insgesamt
    0.82
    __':
    0.77
    '])
    0.75
    OVERALL
    0.75
    __':
    0.73
    __":
    0.71
     Altogether
    0.70
    Act Density 0.002%

    No Known Activations