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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or the phrase "who knows."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.19
    бÑĢа
    -0.18
    remen
    -0.17
    rrha
    -0.15
    obuf
    -0.15
    utenberg
    -0.14
    NST
    -0.14
    untu
    -0.14
    ÏĥÏĦα
    -0.14
    ÑĢик
    -0.14
    POSITIVE LOGITS
    Į
    0.15
    friendly
    0.14
    ys
    0.14
    lia
    0.14
    rr
    0.14
     anymore
    0.14
    å¾Ħ
    0.14
     Gate
    0.14
    endo
    0.13
     cubic
    0.13
    Act Density 0.013%

    No Known Activations