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

    Neuronpedia

    INDEX
    Explanations

    references to guides or guidance within the text

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

    guide rail, guide bolt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.52
     randomNumber
    -0.48
    <bos>
    -0.45
     Massachusetts
    -0.43
    OMEM
    -0.42
    mpton
    -0.42
    océan
    -0.41
    RetentionPolicy
    -0.41
    ntos
    -0.41
     présidenti
    -0.40
    POSITIVE LOGITS
     guide
    1.98
    guide
    1.86
    Guide
    1.84
     Guide
    1.84
     GUIDE
    1.75
     guides
    1.64
    GUIDE
    1.62
     Guides
    1.57
    Guides
    1.47
    guides
    1.40
    Act Density 0.009%

    No Known Activations