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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude, appreciation, and support

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toggle
    -0.75
     guiActiveUn
    -0.62
     Worse
    -0.61
    umably
    -0.60
    edit
    -0.60
    udo
    -0.57
     filler
    -0.57
     Panic
    -0.55
     dummy
    -0.55
    imp
    -0.54
    POSITIVE LOGITS
     courageous
    0.83
     wonderful
    0.82
     sacrific
    0.79
     compassionate
    0.77
     multicultural
    0.77
     excellence
    0.76
    cellence
    0.75
     responsibly
    0.74
     vibrant
    0.74
     magnificent
    0.74
    Act Density 2.020%

    No Known Activations