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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rows
    -0.16
    in
    -0.15
    omi
    -0.15
    oulos
    -0.14
    icon
    -0.14
    iously
    -0.14
    rians
    -0.14
    onde
    -0.14
    ahr
    -0.14
    aman
    -0.14
    POSITIVE LOGITS
    ,[],
    0.16
    radu
    0.16
    anova
    0.14
     piece
    0.14
    chez
    0.13
    esome
    0.13
    lub
    0.13
    ãĥıãĤ¤
    0.13
    539
    0.13
    à¹īาว
    0.13
    Act Density 0.130%

    No Known Activations