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

    Neuronpedia

    INDEX
    Explanations

    prepositions and possessive pronouns indicating relationships between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     persons
    -0.16
    ifen
    -0.15
     Intervention
    -0.14
     (
    -0.14
    cott
    -0.13
    -0.13
     person
    -0.13
    gni
    -0.13
     ðŁ
    -0.13
     Persons
    -0.13
    POSITIVE LOGITS
    kers
    0.16
    UNE
    0.16
    illis
    0.15
    éŁ³æ¥½
    0.14
    ฯ
    0.14
    UBE
    0.14
    oppers
    0.14
    HI
    0.14
    å§Ķåijĺ
    0.14
    405
    0.14
    Act Density 0.008%

    No Known Activations