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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Moines
    -0.68
    hoe
    -0.67
    istor
    -0.65
     Bout
    -0.65
    greg
    -0.64
    Lv
    -0.62
     Store
    -0.60
     forum
    -0.58
     Educ
    -0.58
     Economist
    -0.57
    POSITIVE LOGITS
     surely
    0.87
    yrinth
    0.81
     certainly
    0.80
     undoubtedly
    0.79
     indeed
    0.77
     doubtless
    0.76
     definitely
    0.75
    nt
    0.73
    ajor
    0.72
    hes
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.