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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     warnings
    -0.68
     Opinion
    -0.60
    houses
    -0.60
    hide
    -0.59
    anna
    -0.59
    mong
    -0.59
    oni
    -0.58
    в
    -0.58
    house
    -0.57
    aneous
    -0.57
    POSITIVE LOGITS
     feas
    0.71
    alach
    0.71
    CG
    0.69
    aleigh
    0.68
    patrick
    0.68
    successfully
    0.68
     grounding
    0.68
    ufact
    0.66
    iem
    0.65
    quartered
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.