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

    Neuronpedia

    INDEX
    Explanations

    mentions of shared resources or spaces for collaboration

    oai_token-act-pair · gpt-3.5-turbo

    references to shared resources or communal concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paio
    -0.79
    vernment
    -0.75
    ange
    -0.73
    mental
    -0.72
    eeks
    -0.70
    annis
    -0.70
    isma
    -0.69
    lectic
    -0.68
    esa
    -0.67
     desper
    -0.67
    POSITIVE LOGITS
    cro
    0.91
     shared
    0.75
    hare
    0.74
     Sharing
    0.72
     Shared
    0.70
    Ó
    0.70
     Dunham
    0.69
     encour
    0.68
     shares
    0.68
     sharing
    0.67
    Act Density 0.013%

    No Known Activations