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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    luaj
    -1.11
    pite
    -0.79
    ¯¯
    -0.75
    ĪĴ
    -0.73
    dylib
    -0.72
    sbm
    -0.72
    abi
    -0.71
    olor
    -0.70
    HUD
    -0.69
    ¯
    -0.69
    POSITIVE LOGITS
     editing
    0.63
     entry
    0.63
     passages
    0.59
     mell
    0.59
     Bieber
    0.59
     leaked
    0.58
     Amanda
    0.57
     itiner
    0.57
     exh
    0.57
     Cannes
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.