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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    2.13
    <unused1201>
    2.13
    퍁
    2.12
    𐰽
    2.07
    𒄖
    2.05
    ynucleaires
    2.05
    𒇫
    2.04
    𒌌
    2.04
    yLint
    2.04
    sbParams
    2.02
    POSITIVE LOGITS
     this
    1.75
     the
    1.67
     it
    1.53
     The
    1.41
     that
    1.36
    1.35
    The
    1.32
     which
    1.30
    this
    1.26
     a
    1.26
    Act Density 0.479%

    No Known Activations