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

    Neuronpedia

    INDEX
    Explanations

    concepts related to virtue and moral characteristics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Roskov
    -1.00
     дописавши
    -0.90
    évaluateur
    -0.82
    endpush
    -0.82
    Aidan
    -0.78
    TAINMENT
    -0.77
    HasAnnotation
    -0.77
     Ander
    -0.75
    bouts
    -0.75
     plagio
    -0.75
    POSITIVE LOGITS
     Vir
    1.53
     vir
    1.45
    vir
    1.38
     VIR
    1.34
    Vir
    1.32
     virtue
    1.23
     virulence
    1.12
    VIR
    1.11
     Virtue
    1.09
    Virt
    1.05
    Act Density 0.006%

    No Known Activations