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

    Neuronpedia

    INDEX
    Explanations

    HTML closing tags and references to web addresses

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.62
    -
    -0.55
     "
    -0.53
     Dr
    -0.49
    i
    -0.49
    
    -0.49
    ので
    -0.49
    aar
    -0.49
    lds
    -0.48
    Ả
    -0.48
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.85
     kasarigan
    0.83
     itſelf
    0.78
    hiza
    0.78
    تقاوى
    0.75
     $_"
    0.72
    хьтан
    0.72
     snippetHide
    0.69
     quartzite
    0.69
    mergeFrom
    0.69
    Act Density 0.007%

    No Known Activations