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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating rules or obligations within a legal or regulatory context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    weed
    -0.44
    azo
    -0.41
    UFC
    -0.41
     boo
    -0.40
     algae
    -0.39
     sunscreen
    -0.38
     pic
    -0.38
     ALS
    -0.37
     kids
    -0.37
     selfie
    -0.37
    POSITIVE LOGITS
     moreover
    0.49
    etheless
    0.48
     scholars
    0.47
     scholar
    0.47
    itud
    0.46
     historian
    0.45
    minist
    0.45
    ĸļ
    0.45
     neocons
    0.44
     foremost
    0.44
    Act Density 2.179%

    No Known Activations