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

    Neuronpedia

    INDEX
    Explanations

    references to diversity and anti-discrimination policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .ManyToMany
    -0.16
    artz
    -0.15
    serter
    -0.15
    CTION
    -0.15
    ittel
    -0.15
    auen
    -0.14
    FOUNDATION
    -0.14
    _nsec
    -0.14
    aret
    -0.14
    Matchers
    -0.14
    POSITIVE LOGITS
    atl
    0.18
     mainland
    0.15
    adil
    0.15
     unb
    0.15
    ↵
    0.14
    otu
    0.14
     day
    0.14
    ë
    0.14
     resolved
    0.13
     managerial
    0.13
    Act Density 0.424%

    No Known Activations