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

    Neuronpedia

    INDEX
    Explanations

    references to various types of criminals and criminal activities

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

    criminal justice and law

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Buzz
    -0.56
    zaamheid
    -0.53
    guarda
    -0.53
     postponement
    -0.52
    Buzz
    -0.51
    psa
    -0.51
     Pfeffer
    -0.49
     Lighthouse
    -0.49
    झे
    -0.49
     fondness
    -0.49
    POSITIVE LOGITS
     criminal
    1.52
     criminals
    1.48
    Criminal
    1.45
    criminal
    1.41
     Criminal
    1.40
     Crimin
    1.34
     CRIMINAL
    1.31
     crimin
    1.27
     kriminal
    1.15
     criminality
    1.15
    Act Density 0.015%

    No Known Activations