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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    siblings

    np_acts-logits-general · gemini-2.0-flash

    brother sister siblings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ResponseWriter
    -0.51
     naselje
    -0.49
    </tfoot>
    -0.48
     Himo
    -0.47
    falgar
    -0.47
    BeginContext
    -0.46
    Identyfik
    -0.45
    anyard
    -0.45
     rağmen
    -0.44
    lammatory
    -0.44
    POSITIVE LOGITS
     brother
    2.47
     siblings
    2.44
     sister
    2.37
     brothers
    2.35
     sisters
    2.26
     sibling
    2.24
    brother
    2.11
     Brother
    2.02
    Brother
    1.99
     BROTHER
    1.95
    Act Density 0.183%

    No Known Activations