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

    Neuronpedia

    INDEX
    Explanations

    mentions of innocence and claims of wrongful conviction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odom
    -0.17
     fined
    -0.16
     Judgment
    -0.15
     judgement
    -0.15
     Viol
    -0.15
     Substance
    -0.15
    átor
    -0.15
     sm
    -0.14
    zz
    -0.14
    wahl
    -0.14
    POSITIVE LOGITS
     Innoc
    0.46
     innocence
    0.44
     innocent
    0.38
     innoc
    0.30
     wrongful
    0.28
     exon
    0.26
     DNA
    0.24
    inn
    0.24
     Conv
    0.23
     wrongly
    0.23
    Act Density 0.050%

    No Known Activations