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

    Neuronpedia

    INDEX
    Explanations

    patterns or sequences in numerical or coded data

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Демографія
    -0.75
    numerusform
    -0.73
     hendes
    -0.69
     doubtnut
    -0.68
     Italijanski
    -0.67
     Tacitus
    -0.66
    dasarkan
    -0.66
    tagHelperRunner
    -0.64
     itſelf
    -0.63
     المعيارى
    -0.62
    POSITIVE LOGITS
    /
    0.61
    findpost
    0.48
    UpInside
    0.47
    tonode
    0.46
     mid
    0.45
     Great
    0.45
    <bos>
    0.44
    extAlignment
    0.44
     At
    0.43
     match
    0.43
    Act Density 0.008%

    No Known Activations