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

    Neuronpedia

    INDEX
    Explanations

    language related to ethical concerns and professional responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     weirdly
    -1.14
     goddamn
    -1.12
     shitty
    -1.08
     fucked
    -1.07
     dodgy
    -1.02
     iirc
    -1.02
    fuck
    -1.02
     fuck
    -1.01
    Portail
    -0.99
     FUCKING
    -0.99
    POSITIVE LOGITS
     utilizing
    0.71
     می‌باشد
    0.71
    spania
    0.67
     sculptured
    0.65
    maktadır
    0.64
    Utiliz
    0.62
     Utilizing
    0.62
     monies
    0.61
     Somit
    0.60
     skall
    0.59
    Act Density 1.909%

    No Known Activations