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

    Neuronpedia

    INDEX
    Explanations

    references to personal relationships and interpersonal conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     undertaken
    -0.15
     depart
    -0.15
     borne
    -0.14
    RTOS
    -0.14
     undergone
    -0.14
    urchase
    -0.14
     arisen
    -0.14
     begun
    -0.14
     weary
    -0.14
     thrill
    -0.14
    POSITIVE LOGITS
     fucked
    0.25
     fucking
    0.21
     bitch
    0.20
     shit
    0.20
     screwed
    0.20
     fart
    0.19
     fucks
    0.19
     pissed
    0.19
     quit
    0.18
     just
    0.17
    Act Density 0.397%

    No Known Activations