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

    Neuronpedia

    INDEX
    Explanations

    aspects related to comments and interactions on blog posts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibo
    -0.18
    lore
    -0.16
    doch
    -0.16
    ãĥķãĤ©
    -0.15
    retty
    -0.13
    大人
    -0.13
    .isDefined
    -0.13
    orce
    -0.13
    thal
    -0.13
    ptom
    -0.13
    POSITIVE LOGITS
    ازÙĩ
    0.15
    èĺŃ
    0.15
    ÄĽle
    0.14
    AME
    0.14
     DateFormatter
    0.14
    heartbeat
    0.14
    -caret
    0.14
     buá»ķi
    0.13
    ESSAGES
    0.13
    culate
    0.13
    Act Density 0.023%

    No Known Activations