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

    Neuronpedia

    INDEX
    Explanations

    actions related to violent crimes and criminal behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anken
    -0.15
    ãģ¡ãĤĥ
    -0.15
    ãģĵãģĿ
    -0.14
    ãģªãĤĵãģ¦
    -0.14
    ãģ®ãģł
    -0.14
    ñana
    -0.14
    antar
    -0.14
     pog
    -0.13
     Bilg
    -0.13
     inaug
    -0.13
    POSITIVE LOGITS
     allegedly
    0.22
     approximately
    0.18
    约
    0.17
     multiple
    0.16
     several
    0.15
     numerous
    0.15
     estr
    0.15
     à¤ķथ
    0.14
     reportedly
    0.14
     motive
    0.14
    Act Density 0.394%

    No Known Activations