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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    gae
    -0.75
    omorph
    -0.72
    icable
    -0.70
    ikuman
    -0.69
    MpServer
    -0.67
    igr
    -0.65
    oidal
    -0.64
    aceae
    -0.63
     landsl
    -0.62
    abase
    -0.62
    POSITIVE LOGITS
    anish
    0.68
    NL
    0.68
    stakes
    0.66
    official
    0.65
    asse
    0.64
    ARR
    0.61
    RP
    0.60
    lighting
    0.60
    ynski
    0.59
    ingham
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.