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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a collection or combination of items

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "or" appearing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Wi
    -0.64
     condem
    -0.63
    advertisement
    -0.61
    DEF
    -0.61
    Williams
    -0.57
    vd
    -0.57
    Enjoy
    -0.54
     appre
    -0.53
     Globe
    -0.53
    ured
    -0.53
    POSITIVE LOGITS
    ifice
    1.04
     both
    1.01
    chid
    0.90
     two
    0.89
     more
    0.89
    chard
    0.88
     fewer
    0.88
     several
    0.86
    ouple
    0.81
     none
    0.80
    Act Density 0.042%

    No Known Activations