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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their usage in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardon
    -0.17
    æĶ¾åľ¨
    -0.16
    åħ¥ãĤĬ
    -0.15
     yyn
    -0.15
    iterr
    -0.15
    quier
    -0.14
    ãĥĨãĥ«
    -0.14
     Ampl
    -0.14
    mere
    -0.14
    rowned
    -0.14
    POSITIVE LOGITS
     create
    0.31
     produce
    0.28
     creates
    0.26
     produces
    0.26
     producing
    0.25
    create
    0.25
     creating
    0.24
    .create
    0.24
     Create
    0.22
    -create
    0.22
    Act Density 0.008%

    No Known Activations