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

    Neuronpedia

    INDEX
    Explanations

    references to violence and its various forms and implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    horn
    -0.17
    rying
    -0.16
    acter
    -0.16
    ÑĢÑıдÑĥ
    -0.16
    timeofday
    -0.15
    åij³
    -0.15
    edException
    -0.15
    alian
    -0.14
    owitz
    -0.14
    si
    -0.14
    POSITIVE LOGITS
    ERTICAL
    0.15
    ocities
    0.14
    OLUME
    0.14
    ł
    0.14
    argo
    0.13
    vens
    0.13
    _manual
    0.13
    endo
    0.13
    /or
    0.13
    ergy
    0.13
    Act Density 0.028%

    No Known Activations