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

    Neuronpedia

    INDEX
    Explanations

    references to criminal charges or legal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    criminal case

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     descans
    -0.54
    voerd
    -0.54
    Portail
    -0.54
    ülé
    -0.53
    tvguidetime
    -0.53
    HasIndex
    -0.52
    AccessorTable
    -0.52
     hjelp
    -0.51
     tecnológico
    -0.51
     poř
    -0.51
    POSITIVE LOGITS
     criminal
    1.95
     Criminal
    1.88
    Criminal
    1.83
    criminal
    1.76
     CRIMINAL
    1.63
     Crim
    0.94
     crimin
    0.89
     criminality
    0.88
     kriminal
    0.86
     Kriminal
    0.84
    Act Density 0.010%

    No Known Activations