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

    Neuronpedia

    INDEX
    Explanations

    terms associated with social issues and diversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bout
    -0.15
     Sil
    -0.15
    arp
    -0.14
     range
    -0.14
    hai
    -0.14
    tolower
    -0.14
     ãĥį
    -0.13
     Solo
    -0.13
    illos
    -0.13
    riad
    -0.13
    POSITIVE LOGITS
    626
    0.15
    452
    0.15
    Shown
    0.14
    369
    0.14
    418
    0.14
    397
    0.14
    serrat
    0.14
    roke
    0.14
    461
    0.13
    637
    0.13
    Act Density 0.033%

    No Known Activations