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

    Neuronpedia

    INDEX
    Explanations

    terms related to criminal charges and legal classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ture
    -0.17
    ald
    -0.16
    ingu
    -0.16
    çĸĹ
    -0.14
    sea
    -0.14
    stood
    -0.14
     Nielsen
    -0.13
    butt
    -0.13
    ukt
    -0.13
    izu
    -0.13
    POSITIVE LOGITS
    agle
    0.15
    annah
    0.15
    ABLE
    0.15
    able
    0.15
    ancia
    0.14
     Euler
    0.14
    ÑĢÑİ
    0.14
    rics
    0.14
    oad
    0.14
     Tit
    0.14
    Act Density 0.002%

    No Known Activations