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

    Neuronpedia

    INDEX
    Explanations

    words related to various topics such as sports, activism, technology, and personal stories

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns or entities relevant to various topics such as sports, demographics, business, and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fiscal
    -0.68
    lihood
    -0.64
    Contact
    -0.60
     Federal
    -0.58
    ufact
    -0.56
    ospital
    -0.55
     Alpine
    -0.55
    local
    -0.55
    prem
    -0.54
     SAP
    -0.54
    POSITIVE LOGITS
     ain
    0.76
     sucks
    0.75
     rul
    0.75
     pudding
    0.72
     cares
    0.72
     nerds
    0.71
     hates
    0.67
     lovers
    0.66
     drinkers
    0.65
     sucked
    0.65
    Act Density 0.760%

    No Known Activations