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

    Neuronpedia

    INDEX
    Explanations

    first-person statements containing caveats or conditions

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "this"

    np_token-act-pair-logits · gpt-4o-mini

    "this" in different languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     way
    -0.47
    它们
    -0.40
    它們
    -0.40
    getValueAt
    -0.37
     يتيمه
    -0.36
     Here
    -0.35
    respectively
    -0.35
    way
    -0.33
    itatea
    -0.33
    idade
    -0.32
    POSITIVE LOGITS
     this
    2.89
    this
    2.13
     questo
    1.73
     этого
    1.71
     THIS
    1.66
     questa
    1.55
     هذا
    1.52
     этот
    1.52
     diesem
    1.51
     этом
    1.51
    Act Density 7.547%

    No Known Activations