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

    Neuronpedia

    INDEX
    Explanations

    questions and statements related to personal experiences or needs

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

    "I want" or "you want"

    np_acts-logits-general · gemini-2.0-flash

    expressing wants and desires

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ensement
    -0.60
    rapie
    -0.46
    urable
    -0.46
    tawan
    -0.44
    Tazama
    -0.43
    İM
    -0.43
    Hah
    -0.41
    čin
    -0.41
    thoven
    -0.40
    ","\
    -0.40
    POSITIVE LOGITS
     want
    2.67
     wants
    2.32
    want
    2.31
     Want
    2.23
     wanting
    2.22
     wanted
    2.15
    Want
    2.05
     desire
    1.92
    wants
    1.89
     Wants
    1.87
    Act Density 0.764%

    No Known Activations