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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to safety and security measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SetActive
    -0.17
    imore
    -0.15
    ãĥ¼ãĥ³
    -0.15
    Periph
    -0.15
    soles
    -0.15
    rysler
    -0.14
    abet
    -0.14
    .fhir
    -0.14
    ìĦ¼
    -0.14
     odst
    -0.14
    POSITIVE LOGITS
     against
    0.16
     Against
    0.16
     security
    0.15
    Against
    0.15
     safety
    0.15
    659
    0.15
    itch
    0.15
     coverage
    0.15
    ITCH
    0.14
    pron
    0.14
    Act Density 0.277%

    No Known Activations