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

    Neuronpedia

    INDEX
    Explanations

    instances of automated generation in the text

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

    auto-generated content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MessageBoxIcon
    -0.68
     
    -0.63
     ब्रेकडाउन
    -0.63
     témoig
    -0.61
     plufieurs
    -0.59
    LookAnd
    -0.58
    <unused43>
    -0.57
    typeorm
    -0.57
    <unused41>
    -0.57
    <unused8>
    -0.57
    POSITIVE LOGITS
     automatic
    0.63
    generated
    0.63
     automatically
    0.61
     automated
    0.60
    Generated
    0.57
     Generated
    0.54
    自动
    0.52
     generated
    0.51
     Automatic
    0.50
    Automatic
    0.49
    Act Density 0.006%

    No Known Activations