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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating user options or choices

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     EClass
    -0.55
    JspWriter
    -0.52
    cagon
    -0.52
    ::::::::
    -0.51
    cloudflare
    -0.51
    woj
    -0.50
    extField
    -0.50
    Portály
    -0.49
     通販
    -0.48
     GeoNames
    -0.48
    POSITIVE LOGITS
     EconPapers
    0.83
    AndEndTag
    0.71
     tremp
    0.64
    tdessen
    0.62
     rire
    0.61
     vectorielle
    0.61
     väx
    0.60
     iniciales
    0.60
     שוליים
    0.59
     réfugiés
    0.59
    Act Density 0.001%

    No Known Activations