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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal charges and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -valu
    -0.16
     Prostit
    -0.15
    νι
    -0.15
     Assass
    -0.15
    hiba
    -0.15
    eref
    -0.14
    icens
    -0.14
    eroon
    -0.14
    ibern
    -0.14
    icare
    -0.14
    POSITIVE LOGITS
     charged
    0.36
     accused
    0.32
     suspects
    0.29
    charged
    0.28
     charges
    0.28
     suspected
    0.27
     Charg
    0.27
     alleged
    0.27
     charge
    0.25
     suspect
    0.25
    Act Density 0.140%

    No Known Activations