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

    Neuronpedia

    INDEX
    Explanations

    expressions of concern and disappointment regarding communication and transparency issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "you" or "your"

    np_acts-logits-general · gemini-2.0-flash

    addressing you/your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pihaknya
    -0.61
    niejs
    -0.49
    şağı
    -0.48
    Enlaces
    -0.45
    <eos>
    -0.43
     leur
    -0.43
    alucía
    -0.42
     ihnen
    -0.41
     */
    -0.41
    ')],
    -0.41
    POSITIVE LOGITS
     your
    1.70
    your
    1.49
     Your
    1.42
    Your
    1.39
     you
    1.36
     yours
    1.27
     YOUR
    1.21
     youre
    1.21
    YOUR
    1.19
     yourselves
    1.08
    Act Density 0.349%

    No Known Activations