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

    Neuronpedia

    INDEX
    Explanations

    references to time and change, particularly focusing on the passage of days and the concept of things being over or gone

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

    Forget, goodbye, or gone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    下载附件
    -0.43
    Cyfarwyddwr
    -0.40
     GenerationType
    -0.40
     entdecken
    -0.37
     onOptions
    -0.36
    bigcap
    -0.36
     crisis
    -0.35
    onViewCreated
    -0.35
     Lauf
    -0.35
    Scénario
    -0.35
    POSITIVE LOGITS
    Gone
    0.63
     Gone
    0.63
    Forget
    0.53
     GONE
    0.53
     Forget
    0.53
     gone
    0.51
     adieu
    0.51
    goodbye
    0.50
    gone
    0.49
    Goodbye
    0.49
    Act Density 0.060%

    No Known Activations