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

    Neuronpedia

    INDEX
    Explanations

    messages and confirmations of success or failure in file uploads or email processes

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

    Code snippets and related success/failure messages

    np_acts-logits-general · gemini-2.0-flash

    success messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unacceptable
    -0.56
     unattractive
    -0.52
     unsuitable
    -0.51
     undesirable
    -0.50
     unlikely
    -0.49
     unfit
    -0.49
     GenerationType
    -0.49
     disappointing
    -0.48
     unlucky
    -0.48
    InvalidProtocol
    -0.48
    POSITIVE LOGITS
     SUCCESS
    1.21
     success
    1.18
    success
    1.17
    Success
    1.17
     Success
    1.16
    Successfully
    1.14
    SUCCESS
    1.14
     Successfully
    1.12
     successfully
    1.12
     successful
    1.08
    Act Density 0.087%

    No Known Activations