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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "by"

    oai_token-act-pair · gemini-2.0-flash

    the word "By"

    np_token-act-pair-logits · gpt-4o-mini

    by

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     by
    -0.54
    VersionUID
    -0.49
     efficacité
    -0.48
    UVWXYZ
    -0.47
     EdgeInsets
    -0.44
     informée
    -0.44
    しまい
    -0.43
     When
    -0.42
     mantenga
    -0.42
     détru
    -0.41
    POSITIVE LOGITS
     means
    1.91
    means
    1.66
     way
    1.50
     MEANS
    1.49
     Means
    1.46
    Means
    1.45
     virtue
    1.38
     nahilalakip
    1.13
     middel
    1.01
     dint
    0.95
    Act Density 6.326%

    No Known Activations