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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "at" and its various forms and contexts

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

    time and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.66
    ſelf
    -0.65
    ſelves
    -0.62
     eſſ
    -0.62
     ſche
    -0.57
     juſ
    -0.57
     ſta
    -0.56
     viſ
    -0.56
    wiſe
    -0.54
     neceſſ
    -0.54
    POSITIVE LOGITS
    AnchorStyles
    0.57
     afternoon
    0.53
    ConstraintMaker
    0.51
     Numerade
    0.48
     propOrder
    0.47
     pukul
    0.47
    مزید
    0.45
     midnight
    0.45
     morning
    0.44
     الساعة
    0.44
    Act Density 0.016%

    No Known Activations