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

    Neuronpedia

    INDEX
    Explanations

    superlatives and generalizations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a generalization or commonality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edin
    -0.66
    ISA
    -0.62
    isa
    -0.61
    tis
    -0.59
     Suit
    -0.58
     Travels
    -0.58
     Tracks
    -0.58
    glass
    -0.57
    oak
    -0.56
    fred
    -0.56
    POSITIVE LOGITS
     part
    1.34
     sake
    0.91
     parts
    0.85
     purposes
    0.83
     portion
    0.78
    parts
    0.76
    Downloadha
    0.75
    part
    0.70
     reasons
    0.69
     recent
    0.66
    Act Density 0.023%

    No Known Activations