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

    Neuronpedia

    INDEX
    Explanations

    terms associated with danger and mortality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onian
    -0.16
    égor
    -0.15
    _TD
    -0.14
    ausal
    -0.14
    обÑĢаз
    -0.13
    844
    -0.13
    alian
    -0.13
    edom
    -0.13
    441
    -0.13
    .SDK
    -0.13
    POSITIVE LOGITS
     flaw
    0.18
    lest
    0.17
     dose
    0.17
    arp
    0.16
     consequences
    0.15
    áng
    0.15
     blow
    0.15
     Hansen
    0.15
    Prec
    0.15
    ilig
    0.14
    Act Density 0.033%

    No Known Activations