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

    Neuronpedia

    INDEX
    Explanations

    keywords related to danger and threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    껏
    -0.41
     rígida
    -0.38
    RTCK
    -0.38
     aikaa
    -0.35
     työ
    -0.35
    ArgsConstructor
    -0.35
     azules
    -0.35
    tivitas
    -0.35
     táctil
    -0.35
     llorando
    -0.35
    POSITIVE LOGITS
     danger
    1.57
     Danger
    1.45
    danger
    1.42
     threat
    1.40
    Danger
    1.39
     dangers
    1.34
     threats
    1.33
    threat
    1.32
     dangerous
    1.32
     Threat
    1.30
    Act Density 0.285%

    No Known Activations