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

    Neuronpedia

    INDEX
    Explanations

    references to incarceration and related terms

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

    incarcerated or incarceration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.50
    意见
    -0.47
     Spy
    -0.47
    enheim
    -0.46
     Guía
    -0.44
    aiuto
    -0.44
    setList
    -0.43
     advices
    -0.43
    ouncements
    -0.43
     xenia
    -0.43
    POSITIVE LOGITS
     incarcerated
    1.66
     incarceration
    1.44
     Incar
    1.25
    incar
    1.23
     incarcer
    1.22
     incar
    0.91
    carnation
    0.79
     incarnation
    0.79
     incarnate
    0.74
     Correctional
    0.73
    Act Density 0.007%

    No Known Activations