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

    Neuronpedia

    INDEX
    Explanations

    references to job opportunities and invitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idth
    -0.16
     Hurt
    -0.15
    rell
    -0.14
     Rad
    -0.14
    ATO
    -0.14
    alf
    -0.14
    ARGET
    -0.14
    pons
    -0.14
    atoon
    -0.14
    .Messaging
    -0.13
    POSITIVE LOGITS
     åŀ
    0.15
    StringEncoding
    0.15
    ardi
    0.15
    ÏĦÏģ
    0.14
     cross
    0.14
     %=
    0.14
    令
    0.14
     liqu
    0.13
    iek
    0.13
     kicking
    0.13
    Act Density 0.271%

    No Known Activations