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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    onen
    -0.73
    Info
    -0.73
    olini
    -0.72
    Site
    -0.70
    Url
    -0.65
    HQ
    -0.64
    Fac
    -0.64
    IOR
    -0.64
    FLAG
    -0.63
    iard
    -0.63
    POSITIVE LOGITS
     bothering
    0.71
    ngth
    0.69
    duction
    0.68
    icating
    0.68
    hooting
    0.68
     paralyzed
    0.67
     sooner
    0.65
     hovering
    0.65
    etheless
    0.64
    dden
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.