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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the" and conditional phrases involving "if"

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    期刊论文
    -0.36
    Einsatz
    -0.35
     事件
    -0.31
     žá
    -0.30
     Spaß
    -0.29
     chiens
    -0.29
     précip
    -0.29
     Event
    -0.29
     bater
    -0.28
     outbreak
    -0.28
    POSITIVE LOGITS
    SequentialGroup
    0.74
     CURIAM
    0.65
     EconPapers
    0.64
    Cyfeiriadau
    0.63
     للاسماء
    0.59
    AnchorStyles
    0.58
    VYMaps
    0.58
    0.57
     marketers
    0.57
    rungsseite
    0.57
    Act Density 0.000%

    No Known Activations