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

    Neuronpedia

    INDEX
    Explanations

    references to the second person pronoun "you" and variations thereof

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

    Follows "you" with a suggestion or possibility

    np_acts-logits-general · gemini-2.0-flash

    You followed by modals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portale
    -0.77
     AssemblyTitle
    -0.76
    Portail
    -0.76
    AsUp
    -0.76
     مشين
    -0.75
     beginnetje
    -0.66
    windowFixed
    -0.65
    IndentedString
    -0.65
    extAlignment
    -0.64
     pleaſure
    -0.63
    POSITIVE LOGITS
     may
    0.74
     should
    0.69
     might
    0.68
     probably
    0.67
     generally
    0.62
     bör
    0.60
     MIGHT
    0.57
     likely
    0.57
     can
    0.57
     May
    0.57
    Act Density 0.160%

    No Known Activations