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

    Neuronpedia

    INDEX
    Explanations

    terms related to justification and legal reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.72
     Efq
    -0.64
     Verſ
    -0.60
    RegressionTest
    -0.59
     patate
    -0.57
     ***!
    -0.55
     Geiſt
    -0.55
    featureID
    -0.55
    edicated
    -0.52
     SURFACE
    -0.52
    POSITIVE LOGITS
     justified
    0.81
     justify
    0.75
    justify
    0.74
     justifies
    0.72
     justifying
    0.71
     justification
    0.65
    justified
    0.57
     gius
    0.56
     Jus
    0.56
     jus
    0.56
    Act Density 0.173%

    No Known Activations