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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts or forms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    AutoScale
    -0.71
    ftagPool
    -0.63
    paksa
    -0.60
     account
    -0.58
    XtraBars
    -0.58
    USTIN
    -0.57
     AssemblyCulture
    -0.56
    olkien
    -0.56
    âu
    -0.56
    EndContext
    -0.56
    POSITIVE LOGITS
     XHTML
    0.75
     calendriers
    0.66
     Lorsqu
    0.62
    Ведь
    0.62
     hâte
    0.59
    avyzd
    0.58
     suprême
    0.57
    kadot
    0.57
    Feels
    0.57
    zeptember
    0.56
    Act Density 0.028%

    No Known Activations