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

    Neuronpedia

    INDEX
    Explanations

    periods in code

    oai_token-act-pair · gemini-2.0-flash

    peculiar or unusual formatting

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    
    -0.57
     y
    -0.52
    mockito
    -0.49
     xmlns
    -0.49
    zzleHttp
    -0.48
     on
    -0.48
    mberto
    -0.48
    الصفحه
    -0.47
    awaiter
    -0.47
    XtraReports
    -0.47
    POSITIVE LOGITS
     houſe
    0.69
     itſelf
    0.67
    ſelves
    0.65
     SRA
    0.65
     Houſe
    0.64
     uſe
    0.62
     uſed
    0.62
    DataAnnotations
    0.62
     pleaſure
    0.62
    ſelf
    0.61
    Act Density 0.403%

    No Known Activations