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

    Neuronpedia

    INDEX
    Explanations

    references to personal information or personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.85
    IntoConstraints
    -0.73
    awtextra
    -0.65
     propOrder
    -0.65
    matchCondition
    -0.64
     surla
    -0.59
     estekak
    -0.59
    IUrlHelper
    -0.58
    ⓧ
    -0.57
    msgTypes
    -0.55
    POSITIVE LOGITS
     injury
    0.52
     trainer
    0.49
     belongings
    0.47
    ty
    0.46
     vendetta
    0.45
     Injury
    0.45
     hygiene
    0.43
    गत
    0.43
    injury
    0.42
     Trainer
    0.41
    Act Density 0.119%

    No Known Activations