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

    Neuronpedia

    INDEX
    Explanations

    actions and experiences related to enjoyment and sharing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARA
    -0.15
    indh
    -0.15
    theid
    -0.14
     CWE
    -0.14
    anel
    -0.14
     diffuse
    -0.14
    nf
    -0.14
    ara
    -0.14
    ylland
    -0.14
    okino
    -0.14
    POSITIVE LOGITS
    ând
    0.16
    902
    0.15
     Wing
    0.14
     various
    0.14
     history
    0.14
     McGr
    0.14
     ActionTypes
    0.14
     convo
    0.14
     overall
    0.14
    uropean
    0.13
    Act Density 0.023%

    No Known Activations