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

    Neuronpedia

    INDEX
    Explanations

    relative clauses or phrases that provide additional information about a subject or object

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     greateſt
    -0.73
    Portale
    -0.71
     InputDecoration
    -0.70
    IntoConstraints
    -0.70
     feveral
    -0.66
    tagHelperRunner
    -0.65
     snowing
    -0.65
     igång
    -0.65
    ьаж
    -0.64
     fevere
    -0.61
    POSITIVE LOGITS
     who
    0.81
     can
    0.80
     which
    0.78
     qui
    0.72
     will
    0.70
     is
    0.68
     whose
    0.65
    which
    0.65
     would
    0.64
     οποίο
    0.64
    Act Density 0.363%

    No Known Activations