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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    axis
    -0.81
    assian
    -0.81
    onest
    -0.81
    oral
    -0.78
    ivot
    -0.78
    antis
    -0.77
    apped
    -0.76
    lords
    -0.76
    ilion
    -0.75
    apping
    -0.74
    POSITIVE LOGITS
     closure
    0.74
     Subst
    0.73
     Wass
    0.72
     Zoro
    0.70
     Flavoring
    0.67
     deduction
    0.67
     fireball
    0.67
    Reviewer
    0.65
     mustard
    0.65
     NON
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.