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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     nearer
    -0.66
    loading
    -0.64
    isation
    -0.64
     repro
    -0.62
     psy
    -0.62
    istically
    -0.61
     envy
    -0.61
    topic
    -0.61
     convergence
    -0.60
     reception
    -0.60
    POSITIVE LOGITS
    heast
    0.91
    heastern
    0.83
    edo
    0.80
    amins
    0.78
    raints
    0.78
    akens
    0.77
    loo
    0.72
    hovah
    0.71
     Pengu
    0.71
    hower
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.