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

    Neuronpedia

    INDEX
    Explanations

    the word "parents"

    oai_token-act-pair · gpt-3.5-turbo

    references to "parents."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.92
     Kingdoms
    -0.64
    icity
    -0.64
    ranch
    -0.63
     Limbaugh
    -0.62
     Antar
    -0.62
    ocl
    -0.62
     Corrections
    -0.60
     sclerosis
    -0.60
     Stro
    -0.59
    POSITIVE LOGITS
    hetical
    1.37
    hesis
    1.28
    heses
    1.15
    hetically
    1.09
    parents
    0.90
    hood
    0.84
    hes
    0.82
    Parents
    0.80
    chool
    0.75
    hip
    0.74
    Act Density 0.041%

    No Known Activations