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

    Neuronpedia

    INDEX
    Explanations

    capitalized proper nouns, particularly names and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ount
    -0.19
    les
    -0.15
    LS
    -0.15
    LES
    -0.14
    ye
    -0.14
    ÄĽj
    -0.14
     ordered
    -0.14
    cs
    -0.13
     honest
    -0.13
     Ye
    -0.13
    POSITIVE LOGITS
    rej
    0.17
     FileAccess
    0.16
    ichick
    0.15
    ÙĬÙĥا
    0.15
    VRTX
    0.14
    .Xaml
    0.14
     INTERRUPTION
    0.14
    κÏģα
    0.14
    SetValue
    0.14
    adesh
    0.14
    Act Density 0.084%

    No Known Activations