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

    Neuronpedia

    INDEX
    Explanations

    numerical values and descriptors associated with data types in structured information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    4
    -0.92
    3
    -0.89
    5
    -0.78
    7
    -0.75
    6
    -0.74
    1
    -0.70
    2
    -0.69
    8
    -0.68
    9
    -0.56
    ↵↵
    -0.55
    POSITIVE LOGITS
     насељу
    0.71
    +:+
    0.70
    IsMutable
    0.68
          
    0.67
     EconPapers
    0.67
    WriteAttribute
    0.66
    اریخ
    0.61
                
    0.60
              
    0.60
    RefNanny
    0.59
    Act Density 0.032%

    No Known Activations