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

    Neuronpedia

    INDEX
    Explanations

    items on lists

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving lists or enumerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entimes
    -0.78
    imet
    -0.76
    reach
    -0.74
     breeze
    -0.73
    ibling
    -0.71
    aan
    -0.70
    imeter
    -0.67
    clair
    -0.66
     Belfast
    -0.65
    ashtra
    -0.65
    POSITIVE LOGITS
     sorts
    0.92
     items
    0.85
     ingredients
    0.83
     names
    0.81
     entries
    0.80
     keywords
    0.80
     celebrities
    0.77
     grievances
    0.75
     accomplishments
    0.75
     criteria
    0.75
    Act Density 0.096%

    No Known Activations