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

    Neuronpedia

    INDEX
    Explanations

    expressions of commitment and dedication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coma
    -0.18
    ERS
    -0.16
    hints
    -0.16
    eden
    -0.16
    asio
    -0.16
    ÏģιÏĥ
    -0.15
    eil
    -0.15
    dre
    -0.15
    eu
    -0.15
    onde
    -0.15
    POSITIVE LOGITS
    tees
    0.35
    ting
    0.33
    tee
    0.28
    TING
    0.25
    ments
    0.25
    ment
    0.25
    te
    0.24
    TEE
    0.21
    ters
    0.21
     suicide
    0.20
    Act Density 0.018%

    No Known Activations