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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies and research-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stones
    -0.20
    standing
    -0.17
    eyh
    -0.17
    cheng
    -0.17
    ities
    -0.17
    nal
    -0.17
    ality
    -0.15
     nhau
    -0.15
    ity
    -0.15
    ünchen
    -0.15
    POSITIVE LOGITS
    cation
    0.17
    tro
    0.17
    -issue
    0.17
    ogue
    0.16
    emp
    0.15
    vation
    0.15
    ngthen
    0.14
    oga
    0.14
    onis
    0.14
    -option
    0.14
    Act Density 0.041%

    No Known Activations