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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    EStreamFrame
    -0.73
    FML
    -0.64
    ftime
    -0.64
     experienced
    -0.64
    Plot
    -0.64
    Rew
    -0.63
    CP
    -0.63
     announcer
    -0.63
     belie
    -0.62
     camer
    -0.62
    POSITIVE LOGITS
    opl
    0.72
    orate
    0.69
    ister
    0.69
    olithic
    0.67
    opol
    0.67
    ardless
    0.65
    ony
    0.65
    raid
    0.65
    hide
    0.64
    illon
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.