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

    Neuronpedia

    INDEX
    Explanations

    code-related constructs and patterns, particularly those involving functions and data manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INVAL
    -0.15
    aken
    -0.14
    uilder
    -0.14
    erce
    -0.14
    ARAM
    -0.14
     tears
    -0.14
    .AttributeSet
    -0.14
     Deliver
    -0.14
    оÑĢон
    -0.14
    kad
    -0.14
    POSITIVE LOGITS
    ocal
    0.15
    åĢij
    0.15
    аÑĢÑĩ
    0.15
     Hazel
    0.14
    :nth
    0.14
    803
    0.14
    ÙĦØ©
    0.14
    ucch
    0.13
    785
    0.13
    iou
    0.13
    Act Density 0.182%

    No Known Activations