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

    Neuronpedia

    INDEX
    Explanations

    references to violent or controversial actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    scene
    -0.17
    ãĥijãĥ³
    -0.16
    çİ©
    -0.15
    boxed
    -0.15
    fur
    -0.14
     detach
    -0.14
    itez
    -0.14
    'er
    -0.14
    anton
    -0.14
    ayla
    -0.14
    POSITIVE LOGITS
    ecies
    0.22
    eczy
    0.17
    ospace
    0.15
    ģı
    0.15
    bsp
    0.14
    iasi
    0.14
     Loren
    0.14
    sse
    0.14
     Hamm
    0.14
    reeze
    0.14
    Act Density 0.039%

    No Known Activations