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

    Neuronpedia

    INDEX
    Explanations

    references to pregnancy and babies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stos
    -0.52
    ượu
    -0.51
     hinweg
    -0.50
    стую
    -0.50
    وذ
    -0.48
     agences
    -0.48
    fiq
    -0.47
    逅
    -0.47
     hjelp
    -0.47
     ligiloj
    -0.46
    POSITIVE LOGITS
     baby
    4.64
    baby
    4.23
     Baby
    4.18
    Baby
    4.07
     BABY
    3.84
    BABY
    3.54
     babies
    3.52
     Babies
    3.02
    babies
    2.93
     bébé
    2.90
    Act Density 0.046%

    No Known Activations