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

    Neuronpedia

    INDEX
    Explanations

    elements related to introspection and emotional reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.61
    addOn
    -0.58
     &___
    -0.54
    endforeach
    -0.51
    setupUi
    -0.50
    fürst
    -0.48
    ⓧ
    -0.48
     ATTENTION
    -0.47
     muligt
    -0.46
    mentazione
    -0.46
    POSITIVE LOGITS
    AddTagHelper
    0.70
     Brind
    0.65
     embrace
    0.60
     Hind
    0.55
     Embrace
    0.54
    ERING
    0.54
    igree
    0.54
    וויק
    0.54
     embraces
    0.53
     embracing
    0.52
    Act Density 0.387%

    No Known Activations