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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and relational references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chos
    -0.21
    CHO
    -0.20
    cho
    -0.17
     ****************************************************************************
    -0.15
    Choice
    -0.15
    opers
    -0.14
    DES
    -0.14
    бÑĢÑı
    -0.14
    anted
    -0.13
     cho
    -0.13
    POSITIVE LOGITS
    enny
    0.18
    asant
    0.15
     Heck
    0.15
     Huffman
    0.14
    _rng
    0.14
    abaj
    0.14
    æ´»
    0.14
    isay
    0.14
    aldi
    0.14
    ngen
    0.14
    Act Density 0.012%

    No Known Activations