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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    marginHorizontal
    -0.65
     trous
    -0.59
     lucky
    -0.57
    ecin
    -0.57
    anum
    -0.57
    Effec
    -0.55
    vindo
    -0.55
    prüche
    -0.54
     dano
    -0.54
     TECHNI
    -0.54
    POSITIVE LOGITS
    WriteTagHelper
    0.75
     disponibilités
    0.67
     مرئيه
    0.67
    AndEndTag
    0.65
    日閲覧
    0.61
     >=",
    0.61
    ConstraintMaker
    0.61
    RegressionTest
    0.56
    PMailer
    0.54
    DropTable
    0.53
    Act Density 0.016%

    No Known Activations