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

    Neuronpedia

    INDEX
    Explanations

    words related to destruction and defeat

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

    "[something] destroyed by"

    np_acts-logits-general · gemini-2.0-flash

    destroyed by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.55
     المعيارى
    -0.52
    ReusableCell
    -0.50
     '\\;'
    -0.50
    SPATH
    -0.47
    Jeografia
    -0.46
     estekak
    -0.44
     للمعارف
    -0.44
     wireType
    -0.43
    Fordítás
    -0.43
    POSITIVE LOGITS
     destroyed
    0.49
    rmtree
    0.47
     destroying
    0.45
     destroys
    0.45
     destruction
    0.44
    onDestroy
    0.41
     Destroy
    0.40
     onResponse
    0.40
     onDestroy
    0.39
    Destroyed
    0.39
    Act Density 0.596%

    No Known Activations