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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     initComponents
    -0.58
     asing
    -0.57
    ertale
    -0.55
     Mit
    -0.54
    arcoma
    -0.53
    kel
    -0.50
    ada
    -0.50
     kla
    -0.49
    MethodManager
    -0.49
    мит
    -0.48
    POSITIVE LOGITS
    SBATCH
    0.84
     itſelf
    0.74
    hoga
    0.73
     Wikimedijinoj
    0.71
    ſelves
    0.70
    VersionUID
    0.67
     faſt
    0.66
     themſelves
    0.66
     Mahomet
    0.66
    MessageTagHelper
    0.65
    Act Density 0.873%

    No Known Activations