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

    Neuronpedia

    INDEX
    Explanations

    instances of individuals being convicted or charged with a crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allax
    -0.18
    aben
    -0.17
    eref
    -0.17
    atoire
    -0.16
    éŁ¿
    -0.16
    ohana
    -0.15
    infeld
    -0.15
    isay
    -0.15
     ransom
    -0.14
    olina
    -0.14
    POSITIVE LOGITS
     charged
    0.45
    charged
    0.36
     charge
    0.34
     Charg
    0.34
     charges
    0.31
     charging
    0.28
     Charge
    0.27
    charge
    0.27
     found
    0.26
    charges
    0.26
    Act Density 0.093%

    No Known Activations