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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ober
    -0.74
    arity
    -0.73
    lust
    -0.73
    untled
    -0.73
    jl
    -0.71
    ares
    -0.68
    lex
    -0.67
    anes
    -0.65
    vind
    -0.65
    kn
    -0.65
    POSITIVE LOGITS
     undergo
    0.81
    =#
    0.67
    ¶ħ
    0.67
    erning
    0.66
    sburgh
    0.66
    ĨĴ
    0.65
    folios
    0.63
    ãĤ·ãĥ£
    0.63
    ãĤª
    0.62
    ray
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.