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

    Neuronpedia

    INDEX
    Explanations

    instances of documented cases and incidents

    oai_token-act-pair · gpt-3.5-turbo

    words related to reported cases or instances of various issues or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tainment
    -0.67
    sonian
    -0.63
    vation
    -0.63
    aye
    -0.61
     chores
    -0.59
    lasses
    -0.59
     Altern
    -0.59
     Advance
    -0.58
     entr
    -0.57
    raphics
    -0.56
    POSITIVE LOGITS
     involving
    1.30
     occurring
    1.01
     reported
    0.98
     documented
    0.97
     diagnosed
    0.95
     arising
    0.92
     wherein
    0.87
     prosecuted
    0.86
     cited
    0.86
     where
    0.84
    Act Density 0.148%

    No Known Activations