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

    Neuronpedia

    INDEX
    Explanations

    phrases related to violent or threatening actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÐĴС
    -0.15
    tel
    -0.15
    wire
    -0.15
    PACE
    -0.15
     wire
    -0.15
    ewire
    -0.14
    лÑıд
    -0.14
    nova
    -0.14
    iple
    -0.14
    Nova
    -0.14
    POSITIVE LOGITS
    ssel
    0.16
    JNI
    0.16
     Patch
    0.15
    .patch
    0.14
    yonel
    0.14
    037
    0.14
     patch
    0.14
     Nut
    0.13
    Å¡tÃŃ
    0.13
    keys
    0.13
    Act Density 0.085%

    No Known Activations