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

    Neuronpedia

    INDEX
    Explanations

    instances of reflection or looking back on past experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jes
    -0.16
     Bridge
    -0.16
     bridges
    -0.16
     Bridges
    -0.16
     Wor
    -0.15
    obus
    -0.15
     bridge
    -0.15
    å¥ij
    -0.15
    upo
    -0.14
    onia
    -0.14
    POSITIVE LOGITS
    artner
    0.16
    è
    0.15
    elp
    0.14
    ť
    0.14
     moment
    0.14
     ter
    0.14
    installed
    0.13
     Rosenberg
    0.13
     parti
    0.13
    DataProvider
    0.13
    Act Density 0.014%

    No Known Activations