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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.92
     Roskov
    -0.86
     Gers
    -0.84
     aDecoder
    -0.80
     hObject
    -0.79
    SizeMode
    -0.78
     Cly
    -0.78
     CascadeType
    -0.76
    InsertCommand
    -0.76
    WithMany
    -0.75
    POSITIVE LOGITS
     grateful
    1.25
    rateful
    1.11
     thankful
    0.95
     Grateful
    0.90
     gratitude
    0.87
    Unified
    0.82
     meaningful
    0.81
    ogonal
    0.80
     dankbar
    0.79
    grate
    0.74
    Act Density 0.067%

    No Known Activations