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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating preference or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "rather than"

    np_acts-logits-general · gemini-2.0-flash

    rather than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SizeF
    -0.73
    initializeApp
    -0.60
    exels
    -0.55
     وتسجيلات
    -0.54
    même
    -0.54
    entown
    -0.50
    همچنین
    -0.50
    onViewCreated
    -0.49
     فريبيس
    -0.49
    ListModule
    -0.49
    POSITIVE LOGITS
     than
    1.29
    than
    0.96
     THAN
    0.94
     Than
    0.92
    Than
    0.89
    THAN
    0.82
     opting
    0.74
     niż
    0.69
     decât
    0.63
     ніж
    0.62
    Act Density 0.087%

    No Known Activations