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

    Neuronpedia

    INDEX
    Explanations

    repeated numerical patterns and specific formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.95
     <>",
    -0.95
     TextAppearance
    -0.93
     otomatig
    -0.91
     Meksiku
    -0.90
     feroit
    -0.86
     avoient
    -0.86
     '\\;'
    -0.85
    CodedInputStream
    -0.84
    NameInMap
    -0.83
    POSITIVE LOGITS
    ‚¬
    0.57
    '
    0.56
    ↵↵
    0.54
     s
    0.54
    metra
    0.54
    </h3>
    0.53
    ...
    0.50
    Enllaces
    0.49
     
    0.48
     a
    0.47
    Act Density 0.032%

    No Known Activations