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

    Neuronpedia

    INDEX
    Explanations

    actions related to taking care of someone or something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to caregiving and responsibilities toward others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isoft
    -0.74
    buster
    -0.73
    nir
    -0.72
    ingen
    -0.68
    alyst
    -0.67
    jab
    -0.66
    hra
    -0.65
    iasm
    -0.65
    ederal
    -0.65
    wikipedia
    -0.65
    POSITIVE LOGITS
     orphans
    1.32
     wounded
    1.11
     needy
    1.10
     pets
    1.10
     animals
    1.08
     elderly
    1.08
     grandchildren
    1.04
     kittens
    1.02
     neglected
    1.00
     injured
    0.99
    Act Density 0.208%

    No Known Activations