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

    Neuronpedia

    INDEX
    Explanations

    specific names and terms related to legal cases or medical precedents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Anwar
    -0.87
     Crot
    -0.86
     Clegg
    -0.86
     Huntsville
    -0.84
    ♥♥
    -0.83
    tenor
    -0.82
     đạp
    -0.81
     Magdalena
    -0.79
    Magdalena
    -0.79
     Xiong
    -0.78
    POSITIVE LOGITS
     Hawkins
    0.85
    ’.”
    0.79
    ReusableCell
    0.77
     Rankin
    0.77
    slu
    0.74
    bergh
    0.74
    ţa
    0.74
     Meek
    0.73
    ്‍
    0.73
     Elgin
    0.72
    Act Density 2.805%

    No Known Activations