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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing ownership or relationships, particularly indicating possession or familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fern
    -0.17
    rava
    -0.14
    yg
    -0.14
    -php
    -0.14
    orted
    -0.14
    oling
    -0.13
    ãģŁãģĦ
    -0.13
    quare
    -0.13
    ÑģÑĤи
    -0.13
    äge
    -0.13
    POSITIVE LOGITS
     ways
    0.26
     Ways
    0.19
     how
    0.18
    象
    0.16
    å©·
    0.15
    526
    0.14
     dem
    0.14
    ptic
    0.14
     Giles
    0.14
     konkrét
    0.14
    Act Density 0.055%

    No Known Activations