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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

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

    Acknowledgment; gratitude

    np_acts-logits-general · gemini-2.0-flash

    expression of thanks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ？】
    -0.43
    getPost
    -0.43
     Cep
    -0.43
    modelBuilder
    -0.42
     uska
    -0.42
    Ense
    -0.42
     которое
    -0.42
    PreInfinity
    -0.41
     Houſe
    -0.41
     shaft
    -0.41
    POSITIVE LOGITS
    الإنجليزية
    0.76
    Thanks
    0.72
    edoria
    0.69
     thanks
    0.67
     Италијани
    0.67
    клопе
    0.67
    Rujuakan
    0.66
     виправивши
    0.66
     Thanks
    0.65
    曖昧さ回避
    0.65
    Act Density 0.027%

    No Known Activations