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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ages
    -0.76
     pastoral
    -0.73
     awa
    -0.71
    ultan
    -0.69
     indo
    -0.67
     Mour
    -0.66
    herry
    -0.64
     youth
    -0.63
     companions
    -0.63
     tantal
    -0.62
    POSITIVE LOGITS
    çĶ°
    0.84
    WAYS
    0.82
     Statements
    0.71
    ################
    0.70
    UX
    0.69
    metics
    0.69
    omet
    0.69
    zzo
    0.67
    gio
    0.67
    clips
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.