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

    Neuronpedia

    INDEX
    Explanations

    situations involving societal issues and personal struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blocked
    -0.14
     reviewing
    -0.14
     discussing
    -0.14
     bá»ĭ
    -0.14
     bÄĻdÄħ
    -0.14
    ouden
    -0.14
     observing
    -0.14
    ikk
    -0.14
    nga
    -0.13
     experiencing
    -0.13
    POSITIVE LOGITS
     wreck
    0.29
     ro
    0.26
     wreak
    0.25
     strang
    0.24
     sla
    0.24
     demol
    0.24
     damaging
    0.24
     sabot
    0.24
     tort
    0.23
     destroying
    0.23
    Act Density 0.491%

    No Known Activations