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

    Neuronpedia

    INDEX
    Explanations

    phrases related to thoughts, opinions, and reflections

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "of" and related prepositions indicating possession or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DAQ
    -0.88
    estyles
    -0.83
    %%
    -0.79
    iaries
    -0.75
    soever
    -0.71
    aic
    -0.71
    cies
    -0.71
    cedented
    -0.70
    aughtered
    -0.69
    venants
    -0.68
    POSITIVE LOGITS
     wanting
    1.38
     needing
    1.34
     liking
    1.25
     having
    1.19
     being
    1.16
    being
    1.13
     hating
    1.10
     why
    1.10
     how
    1.09
     figuring
    1.05
    Act Density 0.551%

    No Known Activations