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

    Neuronpedia

    INDEX
    Explanations

    instances of high-stakes actions or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Freund
    -0.18
    380
    -0.17
     Cros
    -0.15
     Photography
    -0.14
    389
    -0.14
     Crab
    -0.14
    ington
    -0.14
     arch
    -0.14
    elow
    -0.14
     Studi
    -0.14
    POSITIVE LOGITS
    .aspx
    0.16
    енÑĤи
    0.16
    bjerg
    0.16
    ÏĦÏĤ
    0.15
    stantiate
    0.15
    jerne
    0.15
    eya
    0.14
    ammer
    0.14
    azon
    0.14
    emento
    0.14
    Act Density 0.003%

    No Known Activations