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

    Neuronpedia

    INDEX
    Explanations

    keywords related to demographic identity and cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ka
    -0.32
    nya
    -0.29
    li
    -0.28
    so
    -0.26
    ba
    -0.26
    ger
    -0.26
    ben
    -0.25
    pro
    -0.25
    be
    -0.25
    la
    -0.25
    POSITIVE LOGITS
    Ùĭ
    0.33
    ’nın
    0.28
    'nın
    0.28
    ught
    0.27
    eus
    0.25
    issance
    0.25
    frica
    0.25
    ugh
    0.24
    ughty
    0.22
    esthesia
    0.22
    Act Density 0.884%

    No Known Activations