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

    Neuronpedia

    INDEX
    Explanations

    references to legal actions and criminal justice terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.57
     Numerade
    -0.52
    хьтан
    -0.52
    ContentAlignment
    -0.49
    󠁴
    -0.49
    qtype
    -0.49
    PLE
    -0.49
    redients
    -0.48
     незавершена
    -0.46
     nonUne
    -0.46
    POSITIVE LOGITS
     reacting
    0.47
     Responding
    0.45
     wobec
    0.44
     responding
    0.43
     Reaktion
    0.43
    ORAGE
    0.42
     reacted
    0.42
     after
    0.42
     responses
    0.41
     response
    0.41
    Act Density 0.786%

    No Known Activations