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

    Neuronpedia

    INDEX
    Explanations

    references to suspects in legal or crime-related contexts

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

    suspect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Navi
    -0.48
    getFullYear
    -0.44
     Dalio
    -0.44
    thanes
    -0.43
     Kiri
    -0.43
     Maro
    -0.42
     Paola
    -0.42
    Día
    -0.41
     Orton
    -0.41
     Reim
    -0.41
    POSITIVE LOGITS
     suspect
    1.86
     suspects
    1.48
     suspe
    1.01
     Sus
    0.98
     suspected
    0.98
     sospe
    0.95
    Sus
    0.95
    sus
    0.92
     suspicion
    0.90
     suspicious
    0.87
    Act Density 0.008%

    No Known Activations