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

    Neuronpedia

    INDEX
    Explanations

    expressions or statements of well-wishing and encouragement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to encouragement and wishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Orig
    -0.70
    coded
    -0.66
    sbm
    -0.65
    artments
    -0.65
     constituted
    -0.64
    aneous
    -0.64
     unit
    -0.62
    anded
    -0.61
    installed
    -0.61
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
    POSITIVE LOGITS
     condolences
    0.99
     beware
    0.98
    Happy
    0.95
     patience
    0.95
     thanking
    0.93
     Happy
    0.93
     thankful
    0.92
     caution
    0.90
    Enjoy
    0.89
    Stay
    0.85
    Act Density 0.848%

    No Known Activations