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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate meaning or definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.55
     oprot
    -0.55
     vrijwilli
    -0.51
     utford
    -0.51
    PerformLayout
    -0.50
    fromnode
    -0.50
    طني
    -0.48
    ThroughAttribute
    -0.47
    paraíso
    -0.46
    odyne
    -0.46
    POSITIVE LOGITS
     mean
    3.73
     MEAN
    3.42
     Mean
    3.39
    mean
    3.31
    Mean
    3.16
    MEAN
    3.09
     Means
    2.68
     meant
    2.67
     means
    2.65
    Means
    2.58
    Act Density 0.105%

    No Known Activations