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

    Neuronpedia

    INDEX
    Explanations

    structure and organization in text, particularly related to lists and parameters

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

    before personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    why I feel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    こいつ
    -0.52
     ček
    -0.52
     précis
    -0.52
     rire
    -0.50
    üttel
    -0.49
     vagas
    -0.48
     contextLoads
    -0.48
     Whipple
    -0.48
     videre
    -0.47
    вня
    -0.47
    POSITIVE LOGITS
     preference
    1.04
     preferring
    1.04
     prefer
    1.00
     prefers
    0.92
     Prefer
    0.91
     Preference
    0.90
     preferred
    0.83
     Advantages
    0.77
    prefer
    0.76
    preference
    0.74
    Act Density 0.731%

    No Known Activations