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

    Neuronpedia

    INDEX
    Explanations

    references to romantic relationships and their complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unga
    -0.19
    zel
    -0.17
    iliz
    -0.16
    ddit
    -0.15
    rieved
    -0.15
    λλά
    -0.15
    ëĬ¥
    -0.14
     عÙħÙĦ
    -0.14
    ÑĥÑģÑĤа
    -0.14
     etm
    -0.14
    POSITIVE LOGITS
     recip
    0.26
     whom
    0.16
     treating
    0.16
    ãģ¨ãģ®
    0.15
     mir
    0.14
     conf
    0.14
    wire
    0.14
    ãĤ¥
    0.14
     breadcrumb
    0.14
    uction
    0.14
    Act Density 0.392%

    No Known Activations