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

    Neuronpedia

    INDEX
    Explanations

    repeated patterns or sequences of similar tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    tz.transition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.86
    ]")]
    -0.81
     faſt
    -0.81
    ThroughAttribute
    -0.75
    bootstrapcdn
    -0.75
     XCTest
    -0.74
     tolua
    -0.74
    ſelf
    -0.73
     UIFont
    -0.72
    ſelves
    -0.71
    POSITIVE LOGITS
              
    1.21
                              
    0.89
    0.88
                  
    0.85
                             
    0.84
    3
    0.84
                
    0.84
               
    0.84
                      
    0.84
             
    0.81
    Act Density 0.032%

    No Known Activations