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

    Neuronpedia

    INDEX
    Explanations

    references to abandoned structures or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ureau
    -0.17
     margins
    -0.15
     Tort
    -0.15
    eker
    -0.14
    atchet
    -0.14
     Ter
    -0.14
    coil
    -0.14
    ogo
    -0.14
    Margins
    -0.13
     Tradition
    -0.13
    POSITIVE LOGITS
     decay
    0.20
    decay
    0.18
     abandonment
    0.17
     abandoned
    0.17
    odos
    0.16
    gia
    0.15
    ropical
    0.15
    اض
    0.15
    CTX
    0.15
     abandon
    0.14
    Act Density 0.124%

    No Known Activations