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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "forget" in various forms

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

    forgetting and remembering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awtextra
    -0.47
     виправивши
    -0.36
    lccc
    -0.36
    XU
    -0.33
    """)
    -0.32
    ̸
    -0.32
    \:
    -0.31
     noDo
    -0.30
    annelse
    -0.30
    😦
    -0.29
    POSITIVE LOGITS
    remember
    0.75
    不忘
    0.73
    forgettable
    0.73
     remember
    0.72
     forgot
    0.71
     forgetting
    0.70
    forgot
    0.70
     remembers
    0.70
     pamię
    0.69
     REMEMBER
    0.68
    Act Density 0.003%

    No Known Activations