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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating agreement or acknowledgement in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surla
    -0.70
     Monfieur
    -0.70
     Efq
    -0.64
     ★★★★★
    -0.63
    ])[
    -0.62
    ʲ
    -0.62
    paddingVertical
    -0.62
    .[/
    -0.62
     Theſe
    -0.60
     Majefty
    -0.59
    POSITIVE LOGITS
    ,
    0.73
     jScrollPane
    0.65
     للاسماء
    0.64
    WebMethod
    0.58
    niad
    0.55
    complexContent
    0.54
    InitStruct
    0.53
     resourceCulture
    0.53
    __":
    0.52
    irvana
    0.52
    Act Density 0.246%

    No Known Activations