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

    Neuronpedia

    INDEX
    Explanations

    mentions of family relationships

    oai_token-act-pair · gpt-3.5-turbo

    the mention of familial relationships, specifically mothers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -0.80
    Beg
    -0.79
    rington
    -0.73
    von
    -0.72
    Jean
    -0.70
    Champ
    -0.68
    Hart
    -0.67
    itable
    -0.67
    lat
    -0.66
    hend
    -0.65
    POSITIVE LOGITS
     counselors
    0.67
     cycles
    0.67
    Quantity
    0.67
    archy
    0.66
     choices
    0.66
     unspecified
    0.65
     meanings
    0.65
     DOE
    0.65
     variables
    0.63
     autop
    0.63
    Act Density 0.000%

    No Known Activations