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

    Neuronpedia

    INDEX
    Explanations

    verbs related to sources or origins

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a source or origin of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ink
    -0.72
    airo
    -0.66
     hosp
    -0.63
     Ou
    -0.63
     Disaster
    -0.62
     famine
    -0.60
     twice
    -0.60
    ake
    -0.60
     administer
    -0.60
    lex
    -0.60
    POSITIVE LOGITS
     stems
    3.51
     stemmed
    2.40
     hinges
    1.48
     derives
    1.35
     arises
    1.34
     rests
    1.26
     boils
    1.26
     stemming
    1.23
     underscores
    1.12
     revolves
    1.09
    Act Density 0.012%

    No Known Activations