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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate occurrences and references to specific events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĨĴ
    -2.65
    ¿½
    -2.58
    ³
    -2.57
    ´
    -2.52
    ł
    -2.46
    ĸ´
    -2.46
    ·¸
    -2.45
    ī
    -2.42
    Ĭ
    -2.39
    ı
    -2.35
    POSITIVE LOGITS
    wives
    1.68
    (`
    1.60
     sender
    1.56
    schemas
    1.47
    board
    1.46
    purpose
    1.46
     purposes
    1.41
    poser
    1.40
    medium
    1.40
     constructor
    1.39
    Act Density 0.252%

    No Known Activations