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

    Neuronpedia

    INDEX
    Explanations

    references to the reader or audience, indicating direct engagement

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

    "You" starting a sentence

    np_acts-logits-general · gemini-2.0-flash

    you followed by common phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.69
     tranſ
    -0.65
    esez
    -0.63
    httphttps
    -0.62
    ^(@)
    -0.62
    
    -0.62
    AnchorStyles
    -0.61
     diſt
    -0.61
     AssemblyCompany
    -0.60
     ſeveral
    -0.58
    POSITIVE LOGITS
     YOU
    0.67
     You
    0.65
     can
    0.64
    YOU
    0.63
    You
    0.61
    you
    0.61
     must
    0.60
     MUST
    0.56
     InputDecoration
    0.54
     יו
    0.53
    Act Density 0.146%

    No Known Activations