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

    Neuronpedia

    INDEX
    Explanations

    references to parental roles and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wner
    -0.19
    rd
    -0.17
    ibold
    -0.17
    werk
    -0.15
    stants
    -0.15
    wat
    -0.15
    	↵	↵	↵	↵
    -0.15
    winter
    -0.14
    sar
    -0.14
    walk
    -0.14
    POSITIVE LOGITS
    eral
    0.32
    -child
    0.25
    thood
    0.22
    esco
    0.22
    親
    0.21
    erals
    0.20
    ally
    0.19
    ::__
    0.18
    age
    0.17
    ents
    0.17
    Act Density 0.045%

    No Known Activations