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

    Neuronpedia

    INDEX
    Explanations

    phrases related to belonging, feeling unwanted, feeling detached, and feeling excluded from a group or community

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     indestru
    -0.92
     shenan
    -0.87
     impractica
    -0.85
     intersper
    -0.85
     impra
    -0.81
     reluct
    -0.81
     apprehen
    -0.80
     volon
    -0.75
     catast
    -0.74
     proprement
    -0.73
    POSITIVE LOGITS
    mybatisplus
    0.62
     feeling
    0.56
    InSection
    0.55
     pinulongan
    0.55
     venit
    0.51
    localPosition
    0.51
     compared
    0.50
    feeling
    0.50
    SuccessListener
    0.49
     سكانية
    0.49
    Act Density 0.429%

    No Known Activations