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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    oother
    -0.79
    bec
    -0.78
    akov
    -0.72
    kees
    -0.69
    emale
    -0.69
     Colleg
    -0.66
     Lifetime
    -0.66
    current
    -0.65
     2024
    -0.65
    jl
    -0.65
    POSITIVE LOGITS
    ATER
    0.78
     encro
    0.66
     ag
    0.63
     deserts
    0.63
     gore
    0.62
     pand
    0.62
    ater
    0.60
    ouched
    0.60
    dj
    0.59
    onies
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.