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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships in arguments or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.69
    Alike
    -0.67
     Roskov
    -0.66
     propOrder
    -0.66
    ChildScrollView
    -0.66
    "]();
    -0.64
    ()?;
    -0.63
     onAnimation
    -0.63
    rsiniz
    -0.62
    RegressionTest
    -0.59
    POSITIVE LOGITS
     consist
    0.71
     consiste
    0.68
     polega
    0.66
     consists
    0.64
     primarily
    0.60
     include
    0.58
     каса
    0.57
     Primarily
    0.57
     заключается
    0.56
     justamente
    0.56
    Act Density 0.390%

    No Known Activations