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

    Neuronpedia

    INDEX
    Explanations

    comments or annotations within the code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ehler
    -0.16
    ze
    -0.16
    sar
    -0.14
    ater
    -0.14
    aters
    -0.14
    rozen
    -0.14
    Å¡ÃŃ
    -0.14
    ble
    -0.13
    oron
    -0.13
     deceased
    -0.13
    POSITIVE LOGITS
    olang
    0.15
     Trash
    0.15
    aul
    0.15
    çłĶ
    0.15
    ucz
    0.14
    ews
    0.14
    acco
    0.14
     Cust
    0.14
    ISK
    0.14
    иÑĨ
    0.14
    Act Density 0.003%

    No Known Activations