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

    Neuronpedia

    INDEX
    Explanations

    mentions of death and dying

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    kills
    -0.50
    funeral
    -0.49
     killed
    -0.47
     death
    -0.47
     deaths
    -0.47
    inalg
    -0.47
     killing
    -0.47
    Killed
    -0.46
     kill
    -0.44
     euth
    -0.44
    POSITIVE LOGITS
     للمعارف
    0.92
    djangoproject
    0.90
    lccn
    0.84
    ValueStyle
    0.84
     snippetHide
    0.82
     Roskov
    0.79
     unknownFields
    0.75
    MemoryWarning
    0.75
    jednoc
    0.73
    lemény
    0.72
    Act Density 0.012%

    No Known Activations