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

    Neuronpedia

    INDEX
    Explanations

    indicators of helpfulness in feedback or reviews

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

    helpfulness and votes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.56
     onPostExecute
    -0.54
    AndEndTag
    -0.53
     @"/
    -0.52
     propOrder
    -0.52
     mergeFrom
    -0.52
    parsedMessage
    -0.48
    blitz
    -0.48
    principalTable
    -0.48
    ftagPool
    -0.47
    POSITIVE LOGITS
     helpful
    0.72
    Helpful
    0.71
     Helpful
    0.69
    helpful
    0.65
     útil
    0.63
     Useful
    0.60
     vote
    0.58
    Useful
    0.57
    Useless
    0.56
     unhelpful
    0.55
    Act Density 0.009%

    No Known Activations