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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to uniqueness and distinctive characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    اء
    -0.15
     èĩªåĬ¨çĶŁæĪIJ
    -0.15
    inx
    -0.15
    usk
    -0.15
    SSIP
    -0.15
    bose
    -0.14
    BOSE
    -0.14
    æĺ
    -0.14
    ases
    -0.14
    êtes
    -0.14
    POSITIVE LOGITS
     special
    0.23
     unique
    0.20
     Special
    0.19
    çī¹æ®Ĭ
    0.19
    Unique
    0.18
     SPECIAL
    0.18
     Unique
    0.17
    special
    0.17
     biá»ĩt
    0.17
    (unique
    0.17
    Act Density 0.205%

    No Known Activations