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

    Neuronpedia

    INDEX
    Explanations

    phrases related to giving help or support

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "back" and related themes of support or protection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     graphs
    -0.71
    products
    -0.61
     diagrams
    -0.60
     books
    -0.59
     graph
    -0.59
     details
    -0.57
     grades
    -0.57
     charts
    -0.56
     Newport
    -0.55
    thumbnails
    -0.54
    POSITIVE LOGITS
    ances
    0.84
    stretched
    0.79
    iveness
    0.69
    ede
    0.69
    seless
    0.69
    ANCE
    0.68
    ealous
    0.66
    aea
    0.65
    anced
    0.65
    arious
    0.65
    Act Density 0.209%

    No Known Activations