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

    Neuronpedia

    INDEX
    Explanations

    occurrences of certain initials or abbreviations related to people's names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ystal
    -0.17
    amus
    -0.16
    ledi
    -0.16
    deniz
    -0.16
    ÏĮγ
    -0.15
    SF
    -0.15
    oin
    -0.15
    unks
    -0.15
    ack
    -0.15
    .MoveNext
    -0.14
    POSITIVE LOGITS
    ONES
    0.23
    ansen
    0.19
    affe
    0.19
    eline
    0.18
    il
    0.18
    astr
    0.18
    aks
    0.17
     ones
    0.17
    ones
    0.17
    bara
    0.17
    Act Density 0.024%

    No Known Activations