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

    Neuronpedia

    INDEX
    Explanations

    references to survival and related familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     S
    -0.60
     an
    -0.58
     F
    -0.52
     A
    -0.52
    -
    -0.51
     s
    -0.51
     E
    -0.51
     ‘
    -0.51
     So
    -0.50
     D
    -0.50
    POSITIVE LOGITS
     survived
    1.27
     Survi
    1.04
     unknownFields
    1.02
    ArgsConstructor
    0.99
    存于互联网档案馆
    0.92
    
    0.92
     الحره
    0.92
    survi
    0.92
    Surviving
    0.91
     kasarigan
    0.90
    Act Density 0.074%

    No Known Activations