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

    Neuronpedia

    INDEX
    Explanations

    references to the second person pronoun "you."

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

    Follows "you" as an object

    np_acts-logits-general · gemini-2.0-flash

    you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    certainly
    -0.55
    definitely
    -0.54
     certainly
    -0.53
     apenas
    -0.53
    only
    -0.52
    Only
    -0.52
     definitely
    -0.50
     claro
    -0.49
     doz
    -0.48
     only
    -0.47
    POSITIVE LOGITS
     Roskov
    0.91
    +#+#
    0.91
     nahilalakip
    0.89
    Externé
    0.80
    fjspx
    0.78
    Rujuakan
    0.75
    évaluateur
    0.74
    Билгалдахарш
    0.69
    InvalidProtocol
    0.68
    WireFormatLite
    0.68
    Act Density 0.223%

    No Known Activations