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

    Neuronpedia

    INDEX
    Explanations

    references to productions or works that have gained significant popularity or recognition

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "has" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lex
    -0.69
     trusts
    -0.64
     Framework
    -0.63
     Monitor
    -0.63
     Corpus
    -0.62
    doms
    -0.61
    Distance
    -0.60
    inance
    -0.60
     Consider
    -0.60
     Exercise
    -0.59
    POSITIVE LOGITS
     garnered
    1.27
     been
    1.23
     become
    1.16
     undergone
    1.15
     surfaced
    1.12
     gotten
    1.10
     risen
    1.08
     spawned
    1.06
    been
    1.06
     morphed
    1.04
    Act Density 0.143%

    No Known Activations