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

    Neuronpedia

    INDEX
    Explanations

    concepts related to diversity and inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄĽ
    -0.15
    ÑĨÑİ
    -0.15
    tracer
    -0.14
    ueil
    -0.14
     Raise
    -0.14
    aret
    -0.14
    ãĥ¼ãĥľ
    -0.14
    sa
    -0.14
     Riv
    -0.14
     Sa
    -0.13
    POSITIVE LOGITS
    lor
    0.15
    appe
    0.15
    .factor
    0.14
     znam
    0.13
     Bast
    0.13
     BaseEntity
    0.13
    ено
    0.13
    uning
    0.13
    ehir
    0.13
    rient
    0.13
    Act Density 0.013%

    No Known Activations