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

    Neuronpedia

    INDEX
    Explanations

    political entities and activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    sters
    -0.81
    nai
    -0.77
    thy
    -0.76
     Adults
    -0.74
    SPONSORED
    -0.74
     Mothers
    -0.72
    gdala
    -0.71
    Person
    -0.71
    nikov
    -0.70
    wives
    -0.69
    POSITIVE LOGITS
     rearr
    0.97
     reuse
    0.96
     reorgan
    0.95
     delet
    0.93
     rewrite
    0.93
     recycle
    0.93
     redund
    0.92
     restruct
    0.92
     decom
    0.92
     decomp
    0.91
    Act Density 0.220%

    No Known Activations