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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric strings within punctuation characters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of technical or programming language elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iors
    -0.59
    camp
    -0.58
    ites
    -0.57
    bots
    -0.55
    yrights
    -0.53
    ãĥ©ãĥ³
    -0.52
    tons
    -0.51
     Prospect
    -0.50
    ,...
    -0.50
    rus
    -0.49
    POSITIVE LOGITS
    ña
    0.69
     condem
    0.68
    pload
    0.66
    uana
    0.65
     rul
    0.60
     Lanka
    0.59
    )=(
    0.59
    determination
    0.57
     helicop
    0.54
     Sovere
    0.53
    Act Density 5.124%

    No Known Activations