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

    Neuronpedia

    INDEX
    Explanations

    words related to actions of involvement or communication such as featuring, registering, or inviting

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating relationships or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     depended
    -0.49
     ensued
    -0.44
     ancest
    -0.43
    ersed
    -0.43
     accounted
    -0.42
     taught
    -0.42
     multiplied
    -0.41
    hops
    -0.41
     consulted
    -0.41
     cared
    -0.41
    POSITIVE LOGITS
     RTX
    0.42
    oxide
    0.40
     Wick
    0.39
    yx
    0.38
     Saturday
    0.37
     avert
    0.36
     Wednesday
    0.36
     Sunday
    0.36
     shore
    0.36
     clarify
    0.35
    Act Density 0.885%

    No Known Activations