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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the prefix "com" in words, likely indicating references to communication or community-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bai
    -0.15
    855
    -0.15
    pom
    -0.14
     addCriterion
    -0.14
    perience
    -0.14
    rego
    -0.14
    볨
    -0.14
    383
    -0.14
    oust
    -0.14
     Frederick
    -0.13
    POSITIVE LOGITS
    ewe
    0.15
    leftright
    0.15
     Thanh
    0.14
    erd
    0.14
    uta
    0.14
     unc
    0.14
    ÏĥÏĦε
    0.13
    isy
    0.13
    ãģĭãģĦ
    0.13
     growing
    0.13
    Act Density 0.015%

    No Known Activations