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

    Neuronpedia

    INDEX
    Explanations

    positive affirmations or expressions of approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     greatness
    -0.19
    psilon
    -0.15
    ittest
    -0.15
    elez
    -0.15
    antics
    -0.15
    ors
    -0.15
     goodness
    -0.14
    ousel
    -0.14
    ively
    -0.14
    s
    -0.14
    POSITIVE LOGITS
    reads
    0.34
    bye
    0.31
    night
    0.31
    -quality
    0.30
    ie
    0.29
     Samar
    0.27
     ol
    0.26
     ole
    0.26
    -sized
    0.25
    -news
    0.25
    Act Density 0.088%

    No Known Activations