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

    Neuronpedia

    INDEX
    Explanations

    phrases related to underlying aspects or structures

    oai_token-act-pair · gpt-3.5-turbo

    words related to foundational or core concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    band
    -0.65
     tours
    -0.65
    Lago
    -0.62
     theirs
    -0.62
     selfies
    -0.61
     hers
    -0.61
     Leaves
    -0.60
    quire
    -0.60
    Review
    -0.59
     Missions
    -0.59
    POSITIVE LOGITS
     underlying
    3.68
     underpin
    1.61
     accompanying
    1.33
     overarching
    1.32
     inherent
    1.29
     intrinsic
    1.22
     prevailing
    1.16
     latent
    1.14
     fundamentals
    1.12
     implicit
    1.08
    Act Density 0.019%

    No Known Activations