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

    Neuronpedia

    INDEX
    Explanations

    references to spoilers in content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agi
    -0.16
    ãĥ¼ãĤ
    -0.16
    ument
    -0.15
    avers
    -0.14
    ÙĪاÙĩ
    -0.14
    serrat
    -0.14
     Fri
    -0.14
    ASTE
    -0.14
    patial
    -0.14
    ELY
    -0.14
    POSITIVE LOGITS
     spo
    0.31
    Spo
    0.28
     Spo
    0.28
    spo
    0.24
    ilers
    0.21
     spoil
    0.21
    iler
    0.21
    ils
    0.20
    ilt
    0.19
    orth
    0.19
    Act Density 0.008%

    No Known Activations