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

    Neuronpedia

    INDEX
    Explanations

    terms related to editorial content and boards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esian
    -0.19
    edin
    -0.15
    otti
    -0.15
    vod
    -0.14
    pire
    -0.14
    oog
    -0.14
    orch
    -0.14
    lings
    -0.14
    alus
    -0.14
     rej
    -0.14
    POSITIVE LOGITS
    imentary
    0.16
    urum
    0.15
    oppins
    0.14
    okemon
    0.14
    incinn
    0.14
    .simps
    0.14
    ateral
    0.14
    iere
    0.14
    _UNS
    0.14
    cem
    0.14
    Act Density 0.005%

    No Known Activations