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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing beginnings or introductory elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     only
    -0.20
    only
    -0.18
     ancak
    -0.17
     ONLY
    -0.16
     neither
    -0.15
     právÄĽ
    -0.15
     atleast
    -0.15
     åĦ
    -0.15
     hanya
    -0.15
     least
    -0.15
    POSITIVE LOGITS
     plain
    0.26
    ifying
    0.21
    ifi
    0.21
    ifiable
    0.20
     Plain
    0.20
    plain
    0.18
    ifies
    0.18
    IFI
    0.17
    Plain
    0.17
    ifications
    0.17
    Act Density 0.199%

    No Known Activations