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

    Neuronpedia

    INDEX
    Explanations

    instances of individuals achieving firsts or breaking barriers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enge
    -0.16
    ãĤ¤ãĥī
    -0.15
    674
    -0.15
    ãĥªãĤ¹
    -0.15
    merce
    -0.15
    ayet
    -0.15
    ornings
    -0.15
    ninger
    -0.14
    ocker
    -0.14
    ackson
    -0.14
    POSITIVE LOGITS
     ever
    0.36
    -ever
    0.30
    ever
    0.28
     jamais
    0.23
     woman
    0.22
     Ever
    0.21
     person
    0.21
     EVER
    0.21
     male
    0.21
     female
    0.21
    Act Density 0.051%

    No Known Activations