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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Aires
    -0.88
     Tome
    -0.73
    herer
    -0.73
    Redd
    -0.72
    retty
    -0.72
     Plenty
    -0.72
    eus
    -0.71
    elf
    -0.69
    bane
    -0.69
    OME
    -0.68
    POSITIVE LOGITS
     trial
    0.74
     capt
    0.73
    rial
    0.71
     rigs
    0.66
     pilot
    0.64
    apse
    0.62
     })
    0.61
     feasibility
    0.61
    })
    0.60
    illance
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.