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

    Neuronpedia

    INDEX
    Explanations

    words related to parts or components

    oai_token-act-pair · gpt-3.5-turbo

    elements related to parts and components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ailability
    -0.75
    coni
    -0.72
    MSN
    -0.70
    oggles
    -0.69
    enhagen
    -0.65
    netflix
    -0.65
    theless
    -0.64
    ogle
    -0.63
    ounter
    -0.63
    Spot
    -0.62
    POSITIVE LOGITS
     fold
    0.77
     chew
    0.75
    selage
    0.73
     folds
    0.72
     append
    0.72
     subt
    0.71
     suffice
    0.71
     parcel
    0.71
     interchangeable
    0.69
     layout
    0.67
    Act Density 0.637%

    No Known Activations