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

    Neuronpedia

    INDEX
    Explanations

    sentences that express criticism or lack of engagement in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hra
    -0.17
    .UnitTesting
    -0.16
    .Suppress
    -0.16
    yre
    -0.16
    lam
    -0.15
    atory
    -0.15
    åĦĢ
    -0.15
    ATORY
    -0.14
    ãģķãĤī
    -0.14
    oga
    -0.14
    POSITIVE LOGITS
    endance
    0.17
    hem
    0.16
    ancia
    0.15
    611
    0.15
     Aires
    0.14
    ecut
    0.14
    655
    0.14
    cls
    0.14
    tplib
    0.14
    ContentPane
    0.13
    Act Density 0.210%

    No Known Activations