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

    Neuronpedia

    INDEX
    Explanations

    references to parent-child relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rd
    -0.17
    wner
    -0.16
    wives
    -0.15
    lÃŃÄį
    -0.15
    ibold
    -0.15
    rades
    -0.15
    sar
    -0.14
    ço
    -0.14
    calar
    -0.14
    	↵	↵	↵	↵
    -0.14
    POSITIVE LOGITS
    eral
    0.35
    age
    0.28
    -child
    0.28
    esco
    0.24
    erals
    0.23
    thood
    0.22
    -da
    0.21
    親
    0.21
    ::__
    0.20
    ially
    0.20
    Act Density 0.053%

    No Known Activations