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

    Neuronpedia

    INDEX
    Explanations

    references to violence and murder

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atik
    -0.15
    FLOW
    -0.15
    ceptive
    -0.15
     hostage
    -0.15
    ıt
    -0.15
    ÑĢиз
    -0.15
    .LookAndFeel
    -0.15
     hostages
    -0.15
    apia
    -0.14
    otos
    -0.14
    POSITIVE LOGITS
    á»Ļc
    0.15
     responsible
    0.15
     cul
    0.15
    èIJ½
    0.14
     spoiler
    0.14
     Shadows
    0.14
     pent
    0.14
     spoilers
    0.14
     Responsibility
    0.14
    .pub
    0.14
    Act Density 0.094%

    No Known Activations