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

    Neuronpedia

    INDEX
    Explanations

    phrases related to job responsibilities and qualifications

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

    before dates, and personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    applying for jobs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    didSet
    -0.68
    RenderAtEndOf
    -0.61
    AndEndTag
    -0.54
    geschäft
    -0.54
     lccn
    -0.53
    UserScript
    -0.52
     CGSize
    -0.50
    перь
    -0.50
     immunotherapy
    -0.49
     IndexPath
    -0.48
    POSITIVE LOGITS
    Willing
    0.63
     willing
    0.62
    willing
    0.60
    出版年
    0.59
     Willing
    0.59
    Portail
    0.56
     eager
    0.55
    Portale
    0.55
     CWE
    0.54
     keen
    0.53
    Act Density 0.182%

    No Known Activations