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

    Neuronpedia

    INDEX
    Explanations

    references to legal concepts and claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bolista
    -0.52
    ThroughAttribute
    -0.46
    ubernur
    -0.46
    tyard
    -0.45
     GenerationType
    -0.45
    yntaxException
    -0.43
    phis
    -0.42
    лтемелер
    -0.42
     OMITBAD
    -0.40
     InputDecoration
    -0.40
    POSITIVE LOGITS
     has
    0.89
     exists
    0.80
     happens
    0.75
     was
    0.74
     hasn
    0.66
     tulee
    0.66
     complies
    0.65
     might
    0.64
     étoit
    0.64
     occurs
    0.64
    Act Density 0.804%

    No Known Activations