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

    Neuronpedia

    INDEX
    Explanations

    comparisons of things in terms of quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating changes in conditions or situations over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Miko
    -0.66
     Channel
    -0.65
    ERY
    -0.65
     Gorge
    -0.59
     WWF
    -0.57
    Yep
    -0.57
     largeDownload
    -0.57
    istries
    -0.56
     Katy
    -0.55
    leted
    -0.55
    POSITIVE LOGITS
    enth
    0.72
    gain
    0.72
     ever
    0.71
    pees
    0.70
    athom
    0.70
    nir
    0.69
    cells
    0.68
    inx
    0.67
     Magicka
    0.67
    ":[
    0.66
    Act Density 0.126%

    No Known Activations