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

    Neuronpedia

    INDEX
    Explanations

    references to weapons and violent actions

    oai_token-act-pair · gpt-3.5-turbo

    references to violent actions, threats, or criminal behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jri
    -0.67
     comprom
    -0.61
     Journals
    -0.59
     pse
    -0.58
    ocus
    -0.57
     advoc
    -0.57
     Vaugh
    -0.55
     enthus
    -0.55
     conclud
    -0.54
     Seym
    -0.54
    POSITIVE LOGITS
     auction
    0.57
    ickr
    0.57
     ?
    0.56
    utterstock
    0.55
     cheapest
    0.55
     Copyright
    0.54
     sale
    0.52
     freezer
    0.52
     Built
    0.51
     microwave
    0.50
    Act Density 1.443%

    No Known Activations