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

    Neuronpedia

    INDEX
    Explanations

    terms related to trust, support, and engagement in a community or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uddle
    -0.18
    chie
    -0.16
    rias
    -0.16
    ortho
    -0.15
    izona
    -0.15
    سÛĮÙĨ
    -0.15
    terdam
    -0.15
    ayım
    -0.15
    PickerController
    -0.15
    æk
    -0.15
    POSITIVE LOGITS
     attention
    0.36
     blessing
    0.32
     consent
    0.31
    attention
    0.31
     support
    0.31
     approval
    0.30
     cooperation
    0.30
     permission
    0.30
     blessings
    0.26
     backing
    0.26
    Act Density 0.131%

    No Known Activations