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

    Neuronpedia

    INDEX
    Explanations

    mentions of bodily harm or injury

    oai_token-act-pair · gpt-3.5-turbo

    references to physical injury or harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Developers
    -0.76
    jam
    -0.67
    Arch
    -0.66
    UTC
    -0.65
    OP
    -0.65
    arp
    -0.64
    arch
    -0.63
     developers
    -0.63
    former
    -0.62
     Today
    -0.62
    POSITIVE LOGITS
     bodily
    3.78
     physiological
    1.21
     Bod
    1.13
     genital
    1.10
     bowel
    1.05
    ODY
    1.05
     limbs
    1.05
     disemb
    1.04
     earthly
    1.04
     genitals
    1.01
    Act Density 0.016%

    No Known Activations