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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BibitemShut
    -0.97
    NUMX
    -0.96
     ―――――
    -0.93
    lijck
    -0.92
     leaſt
    -0.89
     doubtnut
    -0.88
     themſelves
    -0.88
     Theſe
    -0.85
     Eſ
    -0.84
    請繼續往下閱讀
    -0.83
    POSITIVE LOGITS
    ,
    0.70
    .
    0.66
     kasarigan
    0.59
    ;
    0.53
     ('
    0.50
     (
    0.48
    rrbracket
    0.46
     ويكيميديا
    0.46
    Enders
    0.45
    rfloor
    0.44
    Act Density 0.128%

    No Known Activations