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

    Neuronpedia

    INDEX
    Explanations

    references to personal preferences and favorites

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

    favorite things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.72
    Personendaten
    -0.66
    EndContext
    -0.59
    ſelves
    -0.59
    IVEREF
    -0.58
    >--}}
    -0.57
    GenerationType
    -0.56
    ſelf
    -0.56
    RTLD
    -0.55
    ppuden
    -0.55
    POSITIVE LOGITS
     favorite
    1.07
     Favorite
    0.96
    favorite
    0.93
    Favorite
    0.91
     favorites
    0.88
     favourite
    0.88
     favorita
    0.82
     favorito
    0.81
    favorites
    0.77
    favourite
    0.75
    Act Density 0.021%

    No Known Activations