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

    Neuronpedia

    INDEX
    Explanations

    interactions and conflicts involving threats and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.16
     plá
    -0.15
     foreign
    -0.15
     Foreign
    -0.15
     ux
    -0.14
    742
    -0.14
    foreign
    -0.14
    beck
    -0.14
    859
    -0.14
     clearColor
    -0.14
    POSITIVE LOGITS
     boycott
    0.22
     boyc
    0.21
     retali
    0.18
     threatened
    0.18
    pun
    0.18
    ç½ļ
    0.17
     threaten
    0.17
     threat
    0.16
     ostr
    0.16
    -threat
    0.15
    Act Density 0.276%

    No Known Activations