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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    tsky
    -0.80
    inelli
    -0.74
    eteria
    -0.71
    ynski
    -0.71
    ao
    -0.69
    pherd
    -0.67
    hner
    -0.66
    ablishment
    -0.65
    oldown
    -0.65
    berman
    -0.65
    POSITIVE LOGITS
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.67
    ustomed
    0.66
    âĹ¼
    0.65
     Hearthstone
    0.64
    AFTA
    0.63
     riches
    0.62
    GBT
    0.62
    esters
    0.61
     Inquiry
    0.58
    runners
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.