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

    Neuronpedia

    INDEX
    Explanations

    references to threats or dangers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etur
    -0.15
    arent
    -0.15
    gere
    -0.14
    ulton
    -0.14
    undra
    -0.14
    ignon
    -0.13
    .compose
    -0.13
     áo
    -0.13
    keit
    -0.13
    vr
    -0.13
    POSITIVE LOGITS
     danger
    0.19
     dangers
    0.18
     hã
    0.17
    ional
    0.17
    stell
    0.17
     Danger
    0.17
    -danger
    0.16
     threat
    0.15
    threat
    0.15
    ome
    0.15
    Act Density 0.049%

    No Known Activations