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

    Neuronpedia

    INDEX
    Explanations

    terms related to firefighting and fire-related incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -1.09
     Мексичка
    -0.93
    theless
    -0.91
    ]").
    -0.90
     hâte
    -0.90
     betweenstory
    -0.89
    הערות
    -0.88
    BibitemShut
    -0.88
    .}~\
    -0.88
    WebVitals
    -0.87
    POSITIVE LOGITS
    Fire
    1.59
     FIRE
    1.56
    fire
    1.55
     Fire
    1.53
     fire
    1.52
    FIRE
    1.48
     fires
    1.38
     Fires
    1.19
    火
    1.17
    fires
    1.16
    Act Density 0.041%

    No Known Activations