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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal charges and criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulty
    -0.15
    oll
    -0.15
    adge
    -0.15
    alf
    -0.14
     fav
    -0.14
     ticks
    -0.14
    orer
    -0.13
    istik
    -0.13
    pu
    -0.13
    ieg
    -0.13
    POSITIVE LOGITS
    RITE
    0.18
    Tam
    0.16
    æĶ¹
    0.15
     Tam
    0.15
    ượng
    0.15
     tam
    0.15
    ê°ľë¥¼
    0.15
    'gc
    0.15
     possession
    0.15
     Continuous
    0.14
    Act Density 0.043%

    No Known Activations