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

    Neuronpedia

    INDEX
    Explanations

    past participles and verbs indicating completed actions

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

    past-tense actions and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.59
     pleaſure
    -0.55
     ſtate
    -0.53
     ſche
    -0.49
     fevere
    -0.44
     purpoſe
    -0.44
     faſt
    -0.43
    grunns
    -0.42
    хьтан
    -0.42
     Houſe
    -0.42
    POSITIVE LOGITS
    lared
    0.68
    ted
    0.68
    osted
    0.65
    lified
    0.63
    ulted
    0.63
    ded
    0.63
     propOrder
    0.63
     Analyzed
    0.62
    outed
    0.62
     Used
    0.61
    Act Density 0.126%

    No Known Activations