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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Instr
    -0.86
     looph
    -0.71
     Afgh
    -0.70
     exting
    -0.69
     abdom
    -0.67
    interstitial
    -0.66
     Michaels
    -0.66
    iosyn
    -0.66
     earthqu
    -0.66
     Hamm
    -0.65
    POSITIVE LOGITS
    ption
    0.84
     certs
    0.82
    rawdownloadcloneembedreportprint
    0.75
    pmwiki
    0.73
    ertodd
    0.71
     Doodle
    0.70
    ilitarian
    0.68
    BLIC
    0.66
    pta
    0.66
    pter
    0.65
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.