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

    Neuronpedia

    INDEX
    Explanations

    expressions of enthusiasm or excitement

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

    excitement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PB
    -0.47
    lük
    -0.47
    assero
    -0.46
    DataBean
    -0.46
     MPP
    -0.46
     Mank
    -0.44
    AutoresizingMask
    -0.44
     Cb
    -0.43
     Ram
    -0.42
    Ӕ
    -0.42
    POSITIVE LOGITS
     excitement
    1.88
     excite
    1.65
    Exciting
    1.58
     exciting
    1.56
     Exciting
    1.55
    Excited
    1.48
    excited
    1.47
     excites
    1.46
     excited
    1.45
     Excited
    1.38
    Act Density 0.006%

    No Known Activations