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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     wrought
    -0.68
     designers
    -0.67
     designer
    -0.67
     surgeon
    -0.66
     doctors
    -0.65
     miner
    -0.64
    apeshifter
    -0.64
    til
    -0.63
     surgeons
    -0.59
    irl
    -0.59
    POSITIVE LOGITS
    esta
    0.80
    ãĥĺ
    0.80
    OUP
    0.75
    Cube
    0.74
    HCR
    0.73
    externalActionCode
    0.69
     SPL
    0.69
    tics
    0.68
    TH
    0.66
    ETS
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.