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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotional responses and obligations related to contracts or commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eker
    -0.17
    abis
    -0.15
    _RET
    -0.15
    ubu
    -0.15
    ŀæĢ§
    -0.14
    burgh
    -0.14
    calar
    -0.14
    agina
    -0.14
    .Linked
    -0.14
    gers
    -0.13
    POSITIVE LOGITS
    ẩn
    0.14
    282
    0.14
     Division
    0.13
     Alley
    0.13
    leigh
    0.13
    EMU
    0.13
    Ñģом
    0.13
     Venez
    0.13
    last
    0.13
    ierz
    0.13
    Act Density 0.008%

    No Known Activations