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

    Neuronpedia

    INDEX
    Explanations

    various welcome messages

    oai_token-act-pair · gemini-2.0-flash

    greetings and welcoming phrases

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

    Welcome

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    passing
    -0.59
     Passing
    -0.56
    tdessen
    -0.54
    Captor
    -0.52
    enschap
    -0.52
    stdc
    -0.52
    tvguidetime
    -0.52
    styleType
    -0.50
     passing
    -0.48
     autorytatywna
    -0.48
    POSITIVE LOGITS
     hadapan
    0.56
     nakalista
    0.56
    ########.
    0.51
    exitRule
    0.50
     createSlice
    0.49
    rungsseite
    0.48
    )$/,
    0.48
     gezet
    0.48
    clearInterval
    0.47
    Jeografia
    0.47
    Act Density 3.849%

    No Known Activations