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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     «
    -0.65
     Nurse
    -0.62
     Aven
    -0.61
    =-=-=-=-
    -0.60
    alysed
    -0.59
    inker
    -0.59
    urtles
    -0.59
    ãĥĥ
    -0.58
     Harley
    -0.58
    anchez
    -0.57
    POSITIVE LOGITS
    leans
    0.71
     anchors
    0.65
    oral
    0.65
     Rings
    0.64
    arning
    0.63
    ORY
    0.62
    ory
    0.62
    sing
    0.61
    FREE
    0.60
    PROV
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.