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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating uncertainty or anticipation of future events

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

    we will see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aikaa
    -0.53
     kysy
    -0.51
    JvmStatic
    -0.48
     meille
    -0.46
     biologique
    -0.45
     prêtres
    -0.43
     hyö
    -0.42
     założ
    -0.40
     imprimible
    -0.40
     Tiefe
    -0.40
    POSITIVE LOGITS
    MMV
    0.64
    
    0.58
     propOrder
    0.57
     مشين
    0.56
    🤷
    0.55
     🤷
    0.52
    ichord
    0.50
     StringTokenizer
    0.50
     digress
    0.48
    EndInit
    0.47
    Act Density 0.013%

    No Known Activations