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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotional or relational states, particularly those expressing difficulties or contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Towers
    -0.17
    aminer
    -0.15
    INU
    -0.15
    yk
    -0.14
    amil
    -0.14
    atalog
    -0.14
    одо
    -0.14
    istik
    -0.14
    ÑĥÑĩа
    -0.13
    nels
    -0.13
    POSITIVE LOGITS
    iegel
    0.16
    ä¸Ģ人
    0.15
    umbling
    0.15
    ingers
    0.15
    ConnectionString
    0.14
    ä¸ĬçļĦ
    0.14
    agraph
    0.13
    ung
    0.13
    uns
    0.13
    anja
    0.13
    Act Density 0.024%

    No Known Activations