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

    Neuronpedia

    INDEX
    Explanations

    attributed quotes

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating quotes or dialogue

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

    colon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Q
    -0.48
    dende
    -0.48
    1
    -0.48
     ton
    -0.47
    q
    -0.46
    Take
    -0.46
     Man
    -0.46
    ker
    -0.46
    file
    -0.46
    rungsseite
    -0.45
    POSITIVE LOGITS
    ^(@)
    0.71
     myſelf
    0.71
     purpoſe
    0.71
     itſelf
    0.70
     leaſt
    0.69
     privatisation
    0.68
     raiſ
    0.68
    potamus
    0.68
     Theſe
    0.67
    BibitemShut
    0.66
    Act Density 0.269%

    No Known Activations