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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "You" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĨи
    -0.16
    loi
    -0.16
    ÃŃt
    -0.16
    ipur
    -0.15
    allon
    -0.14
    .Dot
    -0.14
    ÅĻaz
    -0.14
    оÑıн
    -0.14
    idge
    -0.14
    wright
    -0.14
    POSITIVE LOGITS
    Tube
    0.20
     Tube
    0.19
     tube
    0.19
    ths
    0.18
    fulness
    0.17
    AIT
    0.17
    ermal
    0.16
    кÑĢаÑĹ
    0.15
    (th
    0.15
    tube
    0.15
    Act Density 0.070%

    No Known Activations