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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of 'mother' and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     كومونز
    -0.77
     Danilo
    -0.71
    ség
    -0.70
    %)$
    -0.67
    følgelig
    -0.65
    ardust
    -0.65
    Darius
    -0.64
    żdy
    -0.63
     Nye
    -0.63
     Pickles
    -0.62
    POSITIVE LOGITS
     mothers
    1.69
     mother
    1.61
     Mother
    1.59
     MOTHER
    1.58
     Mothers
    1.57
    Mothers
    1.57
    MOTHER
    1.53
    mother
    1.52
    Mother
    1.48
    mothers
    1.30
    Act Density 0.048%

    No Known Activations