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

    Neuronpedia

    INDEX
    Explanations

    references to family, specifically the terms related to "mom."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rome
    -0.18
    ovna
    -0.17
    andes
    -0.17
    eed
    -0.15
    wright
    -0.15
    urrect
    -0.15
    eer
    -0.15
    ised
    -0.15
    bite
    -0.14
    alls
    -0.14
    POSITIVE LOGITS
    ma
    0.33
    ents
    0.26
    mys
    0.24
    my
    0.22
    preneur
    0.22
    ENTS
    0.20
    å¦Ī
    0.20
    ager
    0.19
    prene
    0.19
    uments
    0.19
    Act Density 0.020%

    No Known Activations