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

    Neuronpedia

    INDEX
    Explanations

    questions and expressions about reasoning and causality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kv
    -0.18
    .scalablytyped
    -0.15
    ]âĢı
    -0.14
    _rg
    -0.13
    IME
    -0.13
    ipher
    -0.13
    ANC
    -0.13
    arios
    -0.13
    swick
    -0.13
     Dumpster
    -0.13
    POSITIVE LOGITS
     Sind
    0.14
     ifs
    0.14
    /stat
    0.14
    lesi
    0.14
    ales
    0.14
    otech
    0.14
    achat
    0.14
    нÑĸвеÑĢ
    0.14
    sonian
    0.14
    enna
    0.14
    Act Density 0.108%

    No Known Activations