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

    Neuronpedia

    INDEX
    Explanations

    terms related to actions or instructions being provided

    oai_token-act-pair · gpt-3.5-turbo

    elements expressing opinions or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emale
    -0.81
     destro
    -0.72
     submar
    -0.70
    anamo
    -0.69
     Seym
    -0.69
     Vaugh
    -0.68
    avorite
    -0.67
     withd
    -0.66
     occas
    -0.65
    aturdays
    -0.64
    POSITIVE LOGITS
     âĢº
    0.73
    lihood
    0.63
     SHARES
    0.62
     largeDownload
    0.62
    ables
    0.59
    ings
    0.57
     ye
    0.57
     Vulkan
    0.57
     Expand
    0.57
     Hemp
    0.56
    Act Density 0.131%

    No Known Activations