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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to securing objects or ensuring safety

    oai_token-act-pair · gpt-3.5-turbo

    references to events and situations related to social dynamics and community interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Entered
    -0.60
     Hob
    -0.60
     Cop
    -0.54
     Construct
    -0.53
    Fu
    -0.53
    Cop
    -0.52
    Merc
    -0.49
    Offic
    -0.49
    Hol
    -0.49
     Celebr
    -0.49
    POSITIVE LOGITS
    essions
    0.71
    urations
    0.61
    espie
    0.60
    iley
    0.60
    OTOS
    0.60
    urdue
    0.58
    adeon
    0.57
    antha
    0.56
    ohm
    0.56
    )|
    0.55
    Act Density 0.465%

    No Known Activations