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

    Neuronpedia

    INDEX
    Explanations

    numerical values, percentages, and specific data related to classifications or results in research contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.84
    afficheront
    -0.79
    Personendaten
    -0.77
    UnusedPrivate
    -0.77
     Exacts
    -0.76
    expandindo
    -0.76
     चीज़ों
    -0.73
    ंदीखरीदारी
    -0.69
     rhestr
    -0.68
    parsedMessage
    -0.67
    POSITIVE LOGITS
     -
    0.71
    €“
    0.57
     what
    0.51
     –
    0.49
    ねる
    0.49
     "
    0.48
     how
    0.48
    说说
    0.47
     proving
    0.47
    ranos
    0.45
    Act Density 0.241%

    No Known Activations