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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the best or most significant qualities of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     happiest
    -0.16
    ico
    -0.16
    aret
    -0.15
     brightest
    -0.15
    iset
    -0.15
    echa
    -0.14
    onna
    -0.14
    agement
    -0.14
     Eh
    -0.14
    éļĽ
    -0.13
    POSITIVE LOGITS
     equivalent
    0.20
    ILLE
    0.17
    ille
    0.16
    .scalablytyped
    0.16
    tÃŃ
    0.15
    /REC
    0.15
    νÏĦ
    0.14
    lsa
    0.14
     tile
    0.14
    á»ĩn
    0.14
    Act Density 0.099%

    No Known Activations