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

    Neuronpedia

    INDEX
    Explanations

    words related to physical damage or destruction

    oai_token-act-pair · gpt-3.5-turbo

    words that start with the letter 'd'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.88
     Remem
    -0.74
    76561
    -0.70
     Isles
    -0.70
    terday
    -0.68
     Nun
    -0.67
    姫
    -0.66
     Dear
    -0.65
     constitu
    -0.65
    ORTS
    -0.64
    POSITIVE LOGITS
    etermin
    1.20
    idd
    1.12
    ashes
    1.07
    ividual
    1.07
    ashing
    1.06
    ams
    1.06
    renched
    1.06
    orm
    1.06
    abb
    1.05
    ivers
    1.05
    Act Density 0.019%

    No Known Activations