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

    Neuronpedia

    INDEX
    Explanations

    references to characters or elements associated with loss and absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jam
    -0.15
    aload
    -0.15
    ItemAt
    -0.14
     Gone
    -0.14
     jam
    -0.14
     Thing
    -0.14
     safe
    -0.14
    ilter
    -0.14
    ç½
    -0.13
    769
    -0.13
    POSITIVE LOGITS
    еж
    0.15
    athi
    0.14
    urgeon
    0.14
    Rus
    0.14
    .ColumnHeader
    0.14
    azer
    0.14
     thuis
    0.14
    938
    0.14
     Swords
    0.14
    upro
    0.14
    Act Density 0.316%

    No Known Activations