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

    Neuronpedia

    INDEX
    Explanations

    phrases related to danger or risk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enance
    -0.19
    CALE
    -0.18
     trá»Ŀi
    -0.17
    arity
    -0.15
     noqa
    -0.15
    NEY
    -0.15
    å±
    -0.15
    tle
    -0.15
    boom
    -0.14
    verts
    -0.14
    POSITIVE LOGITS
    -danger
    0.20
    ously
    0.18
     dangerous
    0.17
     unsafe
    0.17
    unsafe
    0.16
     dangers
    0.15
    danger
    0.15
    ä¸Ķ
    0.15
    ous
    0.14
     Dangerous
    0.14
    Act Density 0.031%

    No Known Activations