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

    Neuronpedia

    INDEX
    Explanations

    references to family dynamics and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     apprent
    -0.17
    ocab
    -0.17
    olest
    -0.14
    kova
    -0.14
    outes
    -0.14
    grave
    -0.14
    еÑģÑı
    -0.14
    icket
    -0.14
    hsi
    -0.14
    Street
    -0.13
    POSITIVE LOGITS
    abras
    0.15
     couples
    0.14
    ents
    0.14
    592
    0.14
    party
    0.14
    .codes
    0.14
    ÙĨس
    0.13
     guests
    0.13
    Cli
    0.13
     Host
    0.13
    Act Density 0.012%

    No Known Activations