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

    Neuronpedia

    INDEX
    Explanations

    phrases related to completeness or entirety

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "whole."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nings
    -0.72
    liest
    -0.68
    intent
    -0.68
    rf
    -0.64
     inputs
    -0.63
     filings
    -0.62
     bids
    -0.61
    akers
    -0.61
    anwhile
    -0.60
    claimed
    -0.60
    POSITIVE LOGITS
    heartedly
    1.14
     bunch
    0.90
     slew
    0.88
     lot
    0.88
    hearted
    0.86
     swath
    0.83
    dozen
    0.82
     raft
    0.78
     thing
    0.76
     dozen
    0.72
    Act Density 0.014%

    No Known Activations