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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "mother" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    references to family members, particularly mothers and fathers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    intensity
    -0.72
    uters
    -0.71
    mble
    -0.68
    atility
    -0.68
    arcity
    -0.67
    estyles
    -0.66
    uers
    -0.66
    ensitivity
    -0.63
    ilateral
    -0.63
    uve
    -0.62
    POSITIVE LOGITS
    hood
    0.86
     uncle
    0.85
    ma
    0.79
     grandmother
    0.78
     aunt
    0.76
     ancestor
    0.74
     niece
    0.72
     disappro
    0.72
     mummy
    0.71
    parents
    0.70
    Act Density 0.076%

    No Known Activations