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

    Neuronpedia

    INDEX
    Explanations

    references to personal ownership and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tsky
    -0.17
    kke
    -0.16
    ARRIER
    -0.16
    icens
    -0.16
    uracy
    -0.15
    gree
    -0.15
     ÑĤи
    -0.15
    OND
    -0.15
    gon
    -0.14
    eden
    -0.14
    POSITIVE LOGITS
     fault
    0.23
     Fault
    0.20
    fault
    0.18
     undo
    0.18
    Ìĥ
    0.18
     responsibility
    0.17
    opsy
    0.16
    sole
    0.16
    Fault
    0.16
    plied
    0.15
    Act Density 0.103%

    No Known Activations