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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specific points in time

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

    at a time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.98
    ActionCreators
    -0.58
    sidemargin
    -0.57
    uxxxx
    -0.57
    ----</
    -0.55
     propOrder
    -0.55
    EndProject
    -0.55
    ACHUSET
    -0.52
    ynchronously
    -0.50
    nodoc
    -0.50
    POSITIVE LOGITS
     चीज़ों
    0.36
    ſelf
    0.33
     Reſ
    0.32
     phase
    0.30
     bet
    0.28
     pezzo
    0.28
    inerja
    0.28
     $_[
    0.28
     ſch
    0.27
    教學
    0.27
    Act Density 0.200%

    No Known Activations