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

    Neuronpedia

    INDEX
    Explanations

    references to the victim within the context of a crime

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Насе
    -0.69
    </b>
    -0.68
     nhật
    -0.64
    Fah
    -0.62
    ouage
    -0.60
    циональный
    -0.60
     doce
    -0.59
     Strauss
    -0.59
    zq
    -0.59
     gre
    -0.59
    POSITIVE LOGITS
     victims
    1.53
     Victims
    1.45
     Victim
    1.35
     victim
    1.23
    victim
    1.19
     victime
    1.13
    Victim
    1.09
     victimes
    1.04
     Opfer
    1.00
     жерт
    0.96
    Act Density 0.007%

    No Known Activations