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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal activity or violent incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    785
    -0.17
     hum
    -0.16
    bjerg
    -0.16
    uzzi
    -0.16
    rophy
    -0.15
    /Dk
    -0.15
     Shared
    -0.14
    åĢĻ
    -0.14
    spb
    -0.14
    istine
    -0.14
    POSITIVE LOGITS
     resist
    0.15
    auer
    0.15
     à¤īसन
    0.14
     stubborn
    0.14
     IsActive
    0.14
    elts
    0.13
     Beats
    0.13
    0.13
     resistant
    0.13
     cooperation
    0.13
    Act Density 0.021%

    No Known Activations