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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency or quantity related to distribution

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     sähkö
    -0.54
    
    -0.51
    kij
    -0.50
    
    -0.49
     Vikipedi
    -0.49
     cuales
    -0.47
     löyty
    -0.46
    meanor
    -0.45
    orney
    -0.45
    specialchars
    -0.44
    POSITIVE LOGITS
    0.69
    sidemargin
    0.67
    Diweddarwch
    0.66
    UnusedPrivate
    0.65
     surla
    0.61
    abestanden
    0.59
    multer
    0.59
    новништво
    0.58
    lained
    0.58
    rrggbb
    0.58
    Act Density 0.023%

    No Known Activations