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

    Neuronpedia

    INDEX
    Explanations

    terms related to crime and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĩ
    -0.18
    arian
    -0.18
    ointment
    -0.17
    tring
    -0.17
    name
    -0.17
    ness
    -0.16
    ctor
    -0.15
    tems
    -0.15
    rais
    -0.15
    iae
    -0.15
    POSITIVE LOGITS
    fully
    0.18
    ully
    0.18
    olvers
    0.18
    fighters
    0.16
     prevention
    0.15
    eam
    0.15
    acht
    0.14
    /dev
    0.14
    ÑĢек
    0.14
    _INSTALL
    0.14
    Act Density 0.010%

    No Known Activations