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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs ending in 'ed'

    oai_token-act-pair · gpt-3.5-turbo

    the word "did" in various contexts, suggesting a focus on past actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.86
     Nun
    -0.74
     Remem
    -0.72
    éĹĺ
    -0.72
     Pastebin
    -0.71
     mosqu
    -0.70
     momentum
    -0.67
     constitu
    -0.67
    OIL
    -0.67
     RIS
    -0.66
    POSITIVE LOGITS
    ynamic
    1.19
    rown
    1.17
    ownt
    1.10
    iamond
    1.09
    ividual
    1.09
    orm
    1.08
    etermined
    1.06
    olph
    1.05
    aniel
    1.04
    olf
    1.04
    Act Density 0.036%

    No Known Activations