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

    Neuronpedia

    INDEX
    Explanations

    descriptions of risky or hazardous situations and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     noqa
    -0.17
    å±
    -0.15
    CALE
    -0.15
    NEY
    -0.15
    ENTA
    -0.15
    enance
    -0.15
    ãģ¡ãĤĩ
    -0.14
    ting
    -0.14
    onian
    -0.14
    arity
    -0.14
    POSITIVE LOGITS
    -danger
    0.21
    ously
    0.18
     dangerous
    0.18
     unsafe
    0.17
    unsafe
    0.16
    arium
    0.16
    ous
    0.15
     dangers
    0.15
    danger
    0.15
    ä¸Ķ
    0.15
    Act Density 0.039%

    No Known Activations