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

    Neuronpedia

    INDEX
    Explanations

    temporal indicators related to events or actions

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

    after and before

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reafon
    -0.45
    Ros
    -0.39
    듦
    -0.39
     reaſon
    -0.39
    magin
    -0.38
    living
    -0.37
     ROS
    -0.36
    mathbb
    -0.35
     houſe
    -0.35
    Bbb
    -0.35
    POSITIVE LOGITS
     After
    0.82
     after
    0.81
    After
    0.81
    after
    0.76
     после
    0.75
     AFTER
    0.72
     después
    0.71
     setelah
    0.71
    katapos
    0.69
    AFTER
    0.68
    Act Density 0.029%

    No Known Activations