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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    bler
    -0.81
    bley
    -0.80
    apo
    -0.77
    osa
    -0.74
    erer
    -0.73
    atche
    -0.72
    ilet
    -0.67
    ophon
    -0.67
    hus
    -0.67
    unte
    -0.66
    POSITIVE LOGITS
     acknowled
    0.77
     behavi
    0.76
    eatures
    0.75
     amplification
    0.72
     acknowledgement
    0.66
     realizing
    0.66
     bullish
    0.65
     realization
    0.65
     optimization
    0.64
     stances
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.