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

    Neuronpedia

    INDEX
    Explanations

    references to specific incidents or events involving violence or attacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibar
    -0.16
     ãĤ±
    -0.14
    OUCH
    -0.14
    олиÑĤ
    -0.14
    /grpc
    -0.14
    =*/
    -0.13
    .RightToLeft
    -0.13
    iten
    -0.13
    ENTA
    -0.13
    ouch
    -0.13
    POSITIVE LOGITS
     Lake
    0.20
     Maid
    0.20
     Adam
    0.19
    Lake
    0.19
     Cameroon
    0.18
     Ful
    0.17
     Northeast
    0.17
    ắn
    0.17
    Adam
    0.16
     Chad
    0.16
    Act Density 0.012%

    No Known Activations