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

    Neuronpedia

    INDEX
    Explanations

    expressions of desire or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "want" or "wanted"

    np_acts-logits-general · gemini-2.0-flash

    want to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CBC
    -0.42
    ↵↵↵↵
    -0.40
    DDG
    -0.38
     Groves
    -0.37
    скоре
    -0.37
     Oakley
    -0.37
     Davis
    -0.37
     Solis
    -0.37
    󠁿
    -0.36
     Steele
    -0.36
    POSITIVE LOGITS
    want
    1.17
     want
    1.15
     WANT
    1.10
    wants
    1.09
    Want
    1.05
     Want
    1.01
     wants
    0.99
    WANT
    0.98
     wanting
    0.98
     wanted
    0.94
    Act Density 0.087%

    No Known Activations