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

    Neuronpedia

    INDEX
    Explanations

    words related to relationships between people

    oai_token-act-pair · gpt-3.5-turbo

    words related to personal relationships and their dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icter
    -0.77
    isoft
    -0.76
    nin
    -0.75
    rikes
    -0.72
    ocument
    -0.70
    mart
    -0.70
    atel
    -0.70
    orah
    -0.70
    strip
    -0.69
    obi
    -0.69
    POSITIVE LOGITS
     regard
    0.92
     regards
    0.88
     respect
    0.75
     impunity
    0.73
     whom
    0.72
     fellow
    0.70
     Jane
    0.70
    stood
    0.69
     Jared
    0.69
     Samantha
    0.68
    Act Density 0.097%

    No Known Activations