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

    Neuronpedia

    INDEX
    Explanations

    words related to arrival or selection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     khá»ıi
    -0.20
     вÑĸд
    -0.20
    (from
    -0.20
     оÑĤ
    -0.20
    uze
    -0.16
     vom
    -0.16
     od
    -0.16
    idal
    -0.15
    æĿ¥çļĦ
    -0.15
    /from
    -0.15
    POSITIVE LOGITS
     fro
    0.32
     rom
    0.27
     fr
    0.25
     form
    0.24
     Fro
    0.23
     fron
    0.20
     trom
    0.19
    fr
    0.17
     frm
    0.16
    adin
    0.16
    Act Density 0.234%

    No Known Activations