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

    Neuronpedia

    INDEX
    Explanations

    phrases describing unusual or extraordinary characteristics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Jank
    -0.73
     crumb
    -0.66
     CMC
    -0.65
     Kirk
    -0.63
     quint
    -0.63
    est
    -0.63
     Kast
    -0.60
     kust
    -0.60
    SceneManagement
    -0.60
     Titre
    -0.60
    POSITIVE LOGITS
    Unusual
    0.94
     Unusual
    0.91
    Geplaatst
    0.86
    unusual
    0.81
     inusual
    0.78
    Exceptional
    0.73
     unusual
    0.71
     Trojans
    0.70
    écial
    0.70
    Madagascar
    0.68
    Act Density 0.009%

    No Known Activations