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

    Neuronpedia

    INDEX
    Explanations

    violent actions and experiences related to oppression and abuse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chal
    -0.15
    ê²°
    -0.14
     compos
    -0.14
    achable
    -0.14
    _except
    -0.14
     distracting
    -0.14
    chia
    -0.13
    ?url
    -0.13
     assass
    -0.13
     hij
    -0.13
    POSITIVE LOGITS
     torture
    0.40
     Tort
    0.39
     beat
    0.39
     TORT
    0.39
     tort
    0.39
     beating
    0.33
    beat
    0.31
     abuse
    0.30
     beaten
    0.30
     physical
    0.29
    Act Density 0.197%

    No Known Activations