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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lder
    -0.65
    hibit
    -0.65
    quit
    -0.65
    quer
    -0.64
    far
    -0.63
    azaki
    -0.62
    bara
    -0.62
    ague
    -0.62
    rentices
    -0.62
    aquin
    -0.61
    POSITIVE LOGITS
    idth
    0.72
    IPP
    0.72
    LOCK
    0.69
    LCS
    0.68
    IFT
    0.67
    ourgeois
    0.67
    IFIC
    0.66
    iquid
    0.63
     Ambro
    0.62
    ãĤ¼
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.