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

    Neuronpedia

    INDEX
    Explanations

    references to mistakes and lessons learned, particularly in the context of safety and audits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.44
     portraits
    -0.42
    enuine
    -0.40
     portrait
    -0.40
     traps
    -0.38
    rungsseite
    -0.38
     cherries
    -0.38
    AddTagHelper
    -0.38
     nowhere
    -0.36
     sprite
    -0.36
    POSITIVE LOGITS
    urably
    0.50
    JsonInclude
    0.48
     disaster
    0.48
    ChildScrollView
    0.44
     lapses
    0.43
     katastro
    0.43
     catastrophe
    0.43
     disastrous
    0.41
    Chất
    0.41
    省市镇
    0.41
    Act Density 0.704%

    No Known Activations