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

    Neuronpedia

    INDEX
    Explanations

    specific names and contextual references related to legal cases and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ASR
    -0.88
     Diri
    -0.83
    ه
    -0.82
     Castig
    -0.79
     FDR
    -0.75
     Duggan
    -0.75
     Oso
    -0.75
     Manuela
    -0.74
     INTERESAR
    -0.74
     Nicolae
    -0.73
    POSITIVE LOGITS
    unschweig
    0.88
     Bragg
    0.79
    betic
    0.74
     Johns
    0.73
    msford
    0.73
    0.71
     Pet
    0.70
    Gemini
    0.69
     Ange
    0.69
     Braunschweig
    0.67
    Act Density 2.290%

    No Known Activations