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

    Neuronpedia

    INDEX
    Explanations

    descriptions of family relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships and human interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )).
    -0.92
    ]."
    -0.91
    ]).
    -0.87
    ?".
    -0.78
    }.
    -0.77
    )."
    -0.76
     thereto
    -0.76
    ?).
    -0.74
    ).[
    -0.71
     thereof
    -0.69
    POSITIVE LOGITS
    quartered
    0.61
     Huntington
    0.59
    undrum
    0.54
    resa
    0.49
    veland
    0.49
    atin
    0.47
    athered
    0.46
    earchers
    0.45
    anchester
    0.44
    ibrary
    0.44
    Act Density 2.760%

    No Known Activations