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

    Neuronpedia

    INDEX
    Explanations

    expressions related to severe health risks or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ByPrimaryKey
    -0.15
    936
    -0.15
     eventual
    -0.14
    èº
    -0.14
    Ïģή
    -0.13
    Alloc
    -0.13
    asse
    -0.13
    Č↵
    -0.13
    ÑĮ
    -0.13
     Stark
    -0.13
    POSITIVE LOGITS
    criptor
    0.15
    .createClass
    0.14
    ruž
    0.14
    inke
    0.14
    ï¸
    0.14
    [a
    0.14
     omas
    0.14
    idget
    0.14
    AMIL
    0.14
     unint
    0.14
    Act Density 0.356%

    No Known Activations