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

    Neuronpedia

    INDEX
    Explanations

    references to travel destinations and natural landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resc
    -0.15
    ibraries
    -0.14
    Semaphore
    -0.14
    rrha
    -0.14
    ullo
    -0.14
    eree
    -0.14
     muž
    -0.14
     enthus
    -0.14
    aycast
    -0.14
    ÑĩеÑĢ
    -0.13
    POSITIVE LOGITS
     formations
    0.22
     Formation
    0.21
     formation
    0.20
     UNESCO
    0.20
    Formation
    0.19
     Discovery
    0.17
     formed
    0.17
     discovery
    0.16
    formation
    0.15
    UN
    0.15
    Act Density 0.044%

    No Known Activations