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

    Neuronpedia

    INDEX
    Explanations

    instances of agreement or consensus in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riere
    -0.18
    èĭĹ
    -0.15
    inati
    -0.14
    leur
    -0.14
    دارÛĮ
    -0.14
     pháºŃn
    -0.14
    /books
    -0.14
    ytic
    -0.14
    خاÙĨÙĩ
    -0.13
    .fromString
    -0.13
    POSITIVE LOGITS
    ably
    0.27
    /dis
    0.25
     that
    0.25
    able
    0.24
     upon
    0.23
     whole
    0.23
     about
    0.22
     rằng
    0.21
     unanimously
    0.20
    ed
    0.20
    Act Density 0.046%

    No Known Activations