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

    Neuronpedia

    INDEX
    Explanations

    references to the reader or audience directly addressing them

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

    Follows "You" (or similar pronoun)

    np_acts-logits-general · gemini-2.0-flash

    you followed by verbs or yourself/guys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.84
     Walkover
    -0.84
    tagHelperRunner
    -0.82
     ویکی‌پدی
    -0.81
    AddTagHelper
    -0.80
     dAtA
    -0.78
    SourceChecksum
    -0.77
     صوتيه
    -0.77
     ModelExpression
    -0.76
    IsContent
    -0.75
    POSITIVE LOGITS
     guys
    1.70
     yourself
    1.10
     GUYS
    1.04
     guy
    1.02
    guys
    0.99
    Guys
    0.98
     Guys
    0.95
    tubers
    0.86
    yourself
    0.77
    '
    0.77
    Act Density 0.189%

    No Known Activations