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

    Neuronpedia

    INDEX
    Explanations

    themes related to diversity and representation in media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Token "diversity" and follow-up words

    np_acts-logits-general · gemini-2.0-flash

    social diversity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.48
    MessageOf
    -0.43
     الحره
    -0.43
     <=",
    -0.42
     individually
    -0.41
    拾
    -0.40
    individ
    -0.39
     Shawn
    -0.38
    Rau
    -0.37
    MessageTagHelper
    -0.37
    POSITIVE LOGITS
    ſelf
    0.53
    WriteBarrier
    0.49
     AssemblyCulture
    0.48
     diversity
    0.48
     quotas
    0.47
    ſelves
    0.45
     myſelf
    0.45
     diversité
    0.44
     memutus
    0.44
     castes
    0.42
    Act Density 0.248%

    No Known Activations