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

    Neuronpedia

    INDEX
    Explanations

    words related to intuition or intuitive solutions

    oai_token-act-pair · gpt-3.5-turbo

    terms relating to intuitive understanding or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pool
    -0.75
    crow
    -0.73
     McGee
    -0.72
    xual
    -0.71
    gre
    -0.70
    onies
    -0.70
    etheus
    -0.69
    izons
    -0.65
    nces
    -0.64
    vous
    -0.64
    POSITIVE LOGITS
     "$:/
    0.91
    uitive
    0.87
     intuitive
    0.84
     shortcut
    0.81
    ostic
    0.74
    anging
    0.71
     disson
    0.70
     shortcuts
    0.70
    oug
    0.70
    unning
    0.68
    Act Density 0.045%

    No Known Activations