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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing preference or choice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opard
    -0.14
     rpt
    -0.14
    ê
    -0.14
    ilians
    -0.14
    rc
    -0.14
    lasses
    -0.14
    rams
    -0.14
    InnerText
    -0.13
     GPLv
    -0.13
    ovsky
    -0.13
    POSITIVE LOGITS
    wayne
    0.19
    çģ£
    0.15
    νον
    0.15
    ibil
    0.14
    igin
    0.14
    iegel
    0.14
    [method
    0.14
    oppins
    0.14
    agos
    0.14
     seal
    0.14
    Act Density 0.085%

    No Known Activations